Tag Archives: Amazon Bedrock AgentCore

AI-powered clinical trial eligibility and safety using Amazon Bedrock AgentCore

Post Syndicated from Sachin Jain original https://aws.amazon.com/blogs/architecture/ai-agents-for-clinical-trial-screening/

AI agents built on Amazon Bedrock AgentCore let clinical trial teams make fast, accurate enrollment decisions while keeping clinicians in control through human-in-the-loop oversight. According to the Tufts Center for the Study of Drug Development, 80 percent of clinical trials miss their enrollment timelines, and each day of delay costs an estimated $500,000.

Today, eligibility decisions rely on manual chart review across fragmented sources — EHR notes, lab results, imaging reports, and medication histories. Study teams spend hours reconstructing each candidate’s history and mapping it to protocol criteria. As protocols grow more complex, this doesn’t scale: screen failure rates stay high and enrollment targets slip.

We show how to architect a Clinical Trial Eligibility and Safety Agent on AWS that assembles patient evidence, evaluates it against protocol criteria, and presents screening recommendations with citations, while clinicians retain final authority and full audit trails. It combines AWS HealthLake for FHIR-native data access, Amazon Bedrock AgentCore for multi-step reasoning, and Amazon Bedrock AgentCore Evaluations for scoring each decision via LLM-as-a-judge and human-in-the-loop. This post is for solution architects, engineering teams, and technology leaders applying AI to clinical trial operations on AWS.

AI agents for clinical trial screening

AI agents with Human-in-the-Loop (HIL) are well-suited for clinical trial eligibility and safety decisions because they address information fragmentation while preserving human clinical judgment. The core problem isn’t a lack of data, but that eligibility and safety signals are scattered across EHR notes, lab portals, imaging reports, and medication histories, forcing study teams to reconstruct each participant’s clinical picture. A knowledge graph addresses this by storing clinical data as entities and the relationships between them, representing each patient, molecule, endpoint, and market as a node with relationships stored as edges. To answer an eligibility or safety question, the agent traverses these edges, going from a diagnosis to its associated labs or a medication to its known interactions, rather than re-querying and joining disconnected sources each time. This structure supports the agent’s preparatory work:

  • Organizing evidence from fragmented sources into a knowledge graph, linking patients, molecules, endpoints, and markets as interconnected nodes.
  • Mapping patient information against protocol criteria.
  • Surfacing relevant passages with citations for clinician review.
  • Highlighting uncertainties that require human judgment.

Critically, the clinician remains the decision-maker. The agent organizes the supporting information. These systems augment rather than replace clinical reasoning — proposing preliminary assessments, flagging edge cases, providing confidence scores, and learning from feedback.

As protocols grow more complex with precision oncology and biomarker-driven eligibility, agents manage multi-step logic and maintain consistency across sites, while deferring final judgment to clinical staff.

Architecture overview

This proposed architecture illustrates how core AWS services can be combined to create an end-to-end clinical trial screening pipeline. AWS HealthLake serves as the FHIR-native clinical data foundation, ingesting and normalizing patient records from disparate EHR systems, lab portals, and imaging archives into a unified, queryable data store. Amazon Bedrock AgentCore orchestrates the multi-step workflow assembling patient profiles, matching them against trial protocols, detecting safety signals, and generating evidence-backed screening recommendations. An Amazon Bedrock Knowledge Bases stores trial protocols, inclusion/exclusion criteria, and safety guidelines. The entire pipeline feeds into a clinician review dashboard where investigators examine agent reasoning, verify citations, and render final decisions. Actions are captured in an immutable audit trail for regulatory compliance.

Architecture diagram showing the clinical trial screening pipeline with AWS HealthLake, Amazon Bedrock AgentCore, and Amazon CloudWatch

Architecture workflow

The screening pipeline operates in the following steps. Each step maps to a distinct phase of the eligibility and safety assessment, from data ingestion through clinician review and continuous monitoring.

Step 1: Clinical data ingestion

AWS HealthLake ingests patient records from EHR systems, lab portals, imaging reports, and medication histories, then normalizes them into FHIR R4 resources for standardized, queryable access.

Step 2: Agent orchestration

Amazon Bedrock AgentCore orchestrates three specialized agents, each scoped to a distinct phase of the screening pipeline. They operate within the Amazon Bedrock AgentCore Runtime, which connects to tools through MCP Gateway, maintains session memory so agents reference earlier findings without re-querying, and enforces identity-based access control for least-privilege data access. A built-in code interpreter handles dynamic calculations such as eGFR or BMI derivation.

Pre-screening agent: The first gate. It resolves three threshold questions: Is the patient’s informed consent valid and current? Does their high-level profile (age, diagnosis category, geography) align with basic enrollment parameters? Have they completed any required washout period? Patients who clear all three advance. Those who don’t receive a documented rejection citing the failing criterion.

Detailed screening agent: The core clinical reasoning engine. It walks through all inclusion and exclusion criteria, retrieving the relevant FHIR resources — Observation for labs, Condition for diagnoses, MedicationStatement for medications — and evaluating each against the protocol threshold. It also reviews organ function, adverse drug reactions, and contraindicated conditions, cross-references medications against the investigational product for interactions, and assesses the overall comorbidity profile for risk combinations no single criterion would catch. The output is a structured determination (Eligible, Ineligible, or Requires Review) with a per-criterion evidence matrix, confidence scores, and a reasoning summary citing source records.

Site & enrollment agent: Once a patient clears screening, it handles operational logistics — matching the patient to the most appropriate site by proximity, capabilities, and investigator availability, then confirming open enrollment capacity. If the preferred site is full, it identifies alternatives and flags the study coordinator.

All three agents operate behind Amazon Bedrock Guardrails, which enforce:

  1. PII/PHI filtering to protect patient health information.
  2. Content safety controls to help prevent clinically inappropriate outputs.
  3. Grounding checks to keep responses anchored in retrieved evidence rather than model parametric knowledge.
  4. Denied topic boundaries to keep agents within their screening scope.

Step 3: LLM-as-judge evaluation

Amazon Bedrock AgentCore Evaluations scores every screening decision using a combination of built-in and custom evaluators across three dimensions:

  1. Clinical accuracy: Correctness of the eligibility determination against patient data, faithfulness to source evidence (not hallucinated justifications), logical coherence across reasoning steps, and context relevance confirming the right protocol and patient records were retrieved.
  2. Operational effectiveness: Response completeness and clarity for coordinators reviewing dozens of patients daily, appropriate use of FHIR queries and knowledge base tools, and end-to-end goal success (did the agent complete the full screening workflow?).
  3. Safety compliance: Custom evaluators verify that safety-critical criteria (lab thresholds, restricted medications, contraindicated conditions) were never skipped, that uncertainties are explicitly acknowledged rather than resolved with false confidence, and that all safety flags route to the appropriate review tier.

Decisions that pass evaluation with high confidence proceed to the clinician dashboard. The system flags those that fall below quality thresholds and routes them to human review with the specific evaluation concern highlighted.

Step 4: Human-in-the-loop review and enrollment

Flagged cases and agent recommendations flow into a tiered clinical review structure:

  1. PI review queue: Principal Investigators review flagged decisions from the LLM Judge, examining the agent’s reasoning chain, verifying citations against source records, and rendering a final determination.
  2. Study coordinator dashboard: Coordinators manage trial logistics, scheduling, and the day-to-day enrollment pipeline, using the agent’s structured outputs to accelerate their workflow.
  3. Patient communication: Outreach and consent updates are coordinated through the dashboard, keeping patients informed of their screening status.
  4. Escalation to medical director: Complex or high-risk cases that exceed the PI’s comfort level are escalated to the Medical Director for final adjudication.

Clinicians retain complete override capability at every stage. When a clinician overrides an agent recommendation, approving a patient the agent flagged or rejecting one it cleared, the system captures the corrected decision and the clinician’s reasoning. These corrections expand the ground truth dataset used by Amazon Bedrock AgentCore Evaluations and surface patterns that inform prompt and retrieval tuning, creating a continuous learning loop where human judgment directly improves agent performance over time.

Step 5: Observability and continuous monitoring

Amazon CloudWatch provides end-to-end observability across all agents, surfacing agent traces (step-by-step execution logs), latency metrics, error rates (failed tool calls, guardrail blocks), judge scores (pass/flag rates per agent), HITL metrics (override rates, review latency), and alarm-based escalation when safety thresholds are breached.

Although the current implementation focuses on screening and enrollment, the same agent orchestration framework, evaluation pipeline, and compliance infrastructure support future post-enrollment monitoring agents such as adverse event detection from lab results and clinical notes, protocol deviation tracking, retention risk prediction, and re-screening triggers when clinical changes affect ongoing eligibility. Each inherits the existing scoring, logging, and auditability without requiring a separate governance framework.

Evaluating agent performance in clinical trial screening with human oversight

The screening pipeline’s credibility rests on two layers: an automated evaluation layer that scores every decision, and a human-in-the-loop (HITL) layer that gives clinicians final authority. LLM-as-Judge (Step 3) decides which cases clinicians see and how they’re prioritized. The HITL workflow (Step 4) decides how clinicians act. Together they form a continuous loop where human judgment both safeguards and improves agent performance. Using Amazon Bedrock AgentCore Evaluations, you build a framework spanning three dimensions: clinical accuracy, operational effectiveness, and safety compliance with built-in and custom evaluators that run continuously.

Clinical accuracy and reasoning

Built-in evaluators check whether the agent gets the determination right and whether its reasoning holds up: Correctness (accurate against the patient’s labs, diagnoses, and medications), Faithfulness (reasoning stays grounded in patient data and protocol, not plausible-sounding invention), Coherence (no logical contradictions across steps), Context relevance (the right protocol and records were retrieved), and Goal success rate (the full workflow ran end to end). Custom LLM-as-Judge evaluators add clinical specifics: Eligibility accuracy (each inclusion/exclusion criterion evaluated correctly) and Criteria coverage (no criteria skipped, especially safety-critical lab thresholds and restricted medications).

Operational effectiveness

Accuracy alone is insufficient, output must fit workflows where coordinators review dozens of patients daily. Helpfulness, conciseness, and relevance confirm a clear, scannable, on-topic determination. Instruction following verifies the expected structured format (patient summary, criteria checklist, determination, justification, safety flags, next steps). Tool selection and parameter accuracy check the agent invoked the right tools with correct inputs.

Safety and responsible behavior

Safety carries the strictest thresholds. Harmfulness detection flags clinically dangerous content; Stereotyping detection makes sure decisions aren’t influenced by demographics beyond protocol requirements. Both trigger immediate review. Custom evaluators target the highest-risk failures: Safety flag detection confirms every significant concern surfaced (contraindicated medications, out-of-range labs, disqualifying conditions, drug interactions), with a single miss treated as critical; Uncertainty acknowledgment makes sure the agent recommends human review on missing or ambiguous data rather than making an overconfident call.

The human-in-the-loop safeguard

When a wrong eligibility call can affect patient safety, human judgment is the final safeguard. A score below threshold routes the case to the HITL workflow.

The three agents together produce an eligibility determination with a confidence score. At trial onset, the clinician sets a confidence threshold. Cases below it or flagged by evaluation reach the clinician dashboard with the specific concern highlighted. Clinicians review the full reasoning and approve, reject, or request more information from the same interface. Their corrections are stored alongside machine-approved records, feeding back into future determinations and continuously improving accuracy.

Review and approval workflow

Review is tiered by complexity: automated pre-screening filters clearly ineligible candidates. Low-complexity cases get expedited review, medium-complexity follow standard protocols, and high-complexity edge cases escalate to senior clinicians. Cases unreviewed beyond set timeframes escalate automatically. Final enrollment decisions, low-confidence cases, experimental therapies, and complex histories require human approval. Routine high-confidence checks proceed automatically.

Audit trails

The system generates immutable audit records in Amazon DynamoDB for every decision, capturing clinician ID, timestamp, patient and trial IDs, outcomes, AI recommendations, and complete workflow execution history. These records are designed to support FDA 21 CFR Part 11 requirements for electronic records and signatures, providing documentation for regulatory inspections and quality assurance. Readers should consult their compliance team and conduct their own assessment. See the AWS compliance resources for further guidance.

Security and compliance

Clinical trial data is among the most sensitive in healthcare. HIPAA, FDA 21 CFR Part 11, GxP, and GDPR require strict controls over how patient data is stored, accessed, and processed, and AI agents reasoning over that data introduce new security considerations. This solution protects data at every layer while maintaining the audit trails and privacy standards regulators require.

AWS HealthLake is HIPAA-eligible with encryption at rest and in transit, access controls, and SMART on FHIR authorization. Amazon Bedrock is HIPAA-eligible, SOC 2 attested, ISO and CSA STAR Level 2 certified, and never shares customer data with model providers. AWS PrivateLink keeps traffic off the public internet.

Amazon Bedrock AgentCore enforces agent boundaries at runtime through declarative authorization policies — readable, deterministic rules, outside application code, defining what the agent can access, invoke, and retrieve. AgentCore runs within your Amazon Virtual Private Cloud (Amazon VPC) for network isolation, and AWS CloudTrail records API calls for an immutable audit trail that can support FDA compliance requirements.

Amazon Bedrock AgentCore Evaluations scores each decision using built-in and custom evaluators with an LLM-as-a-Judge approach. Continuous sampling detects drift, and Amazon CloudWatch alerts teams when quality drops below thresholds — ongoing evidence the agent performs within validated parameters, supporting GxP with minimal manual testing.

Conclusion

In this post, we showed how combining the FHIR-native data foundation of AWS HealthLake
with the multi-step reasoning capabilities of Amazon Bedrock AgentCore turns manual,
fragmented clinical trial screening into an AI-assisted workflow that reduces patient matching
time from days to minutes. Clinical trial enrollment remains one of drug development’s most
resource-intensive bottlenecks, and delayed starts carry heavy financial consequences from lost
patent-protected sell time and operational burn. Clinicians receive organized evidence,
transparent reasoning, and actionable recommendations while retaining full decision authority
and audit traceability.

The impact extends beyond speed: more consistent criteria interpretation across sites, earlier
detection of safety contraindications, and lower screen failure rates. As oncology trial eligibility
criteria grow in complexity — with fewer than 5% of cancer patients enrolling under strict
requirements — this human-in-the-loop approach offers a scalable, compliance-aligned path to
faster, higher-quality recruitment.

Call to action

Ready to accelerate your clinical trial operations? Take the next step:

Implement custom authentication for tools integration using request Lambda interceptor in AgentCore Gateway

Post Syndicated from Nishant Mainro original https://aws.amazon.com/blogs/security/implement-custom-authentication-for-tools-integration-using-request-lambda-interceptor-in-agentcore-gateway/

When deploying AI agents with Amazon Bedrock AgentCore, organizations benefit from built-in modern support for OAuth 2.0, AWS Identity and Access Management (IAM), and API key authentication through Amazon Bedrock AgentCore Gateway. However, some enterprise environments still use legacy authentication mechanisms such as HTTP Basic Authentication (Basic Auth) (RFC 7617). The extensible architecture of AgentCore Gateway enables support for these authentication mechanisms through a request Lambda interceptor—custom code that runs each time an agent calls a tool.

In this post, we show you how to use a request Lambda interceptor to authenticate to a downstream tool API using system credentials, retrieving a service account credential from AWS Secrets Manager and constructing a Basic Auth header. This design keeps credentials isolated from the agent, designed to mitigate exposure through model-driven behavior such as prompt injection.

Important: Basic Auth is an antiquated technology that transmits credentials as Base64-encoded text and should not be used as a long-term authentication strategy. AWS recommends modernizing to OAuth 2.0, SAML, OpenID Connect, or IAM where possible. However, some organizations with legacy workloads choose to decouple authentication modernization from their agentic AI adoption, addressing each on independent timelines. If your environment requires Basic Auth integration as an interim measure, consult your AWS Solutions Architect to evaluate the security trade-offs before proceeding. We’re providing this post as a reusable implementation, but it shouldn’t be construed as an endorsement of Basic Auth, or considered suitable as a long-term solution.

Solution overview

The solution uses a request Lambda interceptor in AgentCore Gateway to retrieve system credentials and construct a Basic Auth header for the downstream tool API. Figure 1 shows the end-to-end flow.

Figure 1: Solution workflow

Figure 1: Solution workflow

  1. The AI agent initiates a tool call over Model Context Protocol (MCP) to the gateway with an inbound JSON Web Token (JWT) issued by a configured identity provider (IdP). The MCP request body contains the tool name and any required parameters. The gateway’s inbound authentication layer validates the token against the IdP specified in the inbound authorizer configuration.
  2. After inbound authentication succeeds, the gateway invokes the request Lambda interceptor, passing the original request payload and headers, including the validated JWT and its embedded claims.
  3. The request Lambda interceptor re-validates the inbound JWT issued by the configured IdP as a defense-in-depth measure, then retrieves the system service account credential from Secrets Manager. The credential is a service account that authenticates the AI agent to the downstream tool.
  4. The interceptor then constructs a compliant Basic Auth header using the system credential and adds it to the outbound request. Because Basic Auth transmits credentials as Base64-encoded text (not encrypted), you must implement relevant compensating controls (e.g., ensure that all communication with the downstream tool API is over TLS, conduct two-person review of Lambda code changes, and so on).

    Note: The system credential stored in Secrets Manager corresponds to a service account in Active Directory (AD). The credential lifecycle requires a one-time manual seed: a system administrator creates the service account in AD and stores the same initial credential in Secrets Manager (necessary because Secrets Manager can’t read a password back from AD). As a security best practice, trigger an immediate rotation after seeding to retire the human-known password using the built-in capabilities of Secrets Manager. From that point forward, Secrets Manager automates the rotation process, periodically generates a new password, and updates both Secrets Manager and AD simultaneously. This eliminates manual credential management in either system. At runtime, the request Lambda interceptor retrieves the current credential from Secrets Manager and presents it to the downstream tool, which validates it against AD. For implementation details on keeping both stores synchronized, see Rotate Active Directory credentials stored in AWS Secrets Manager.

  5. The AgentCore gateway forwards the adjusted request now carrying the custom authentication header to the downstream target tool.
  6. The downstream target tool authenticates the request, processes it, and returns the response to the gateway.
  7. The gateway relays the response back to the AI agent.

Implementation

The following steps walk through configuring the request Lambda interceptor and implementing the core of the authentication transformation logic. You can find the complete sample code at Implementing custom authentication for tools integration using Request Lambda Interceptor.

Step 1: Attach a request Lambda interceptor to your AgentCore Gateway

Configure the AgentCore gateway to invoke a request Lambda interceptor for authentication transformation before forwarding the request to the downstream tool.

Important: You must enable passRequestHeaders configuration. Without it, the request Lambda interceptor can’t receive the request header containing the inbound JWT, and the authentication pattern described in this post will not work.

The following example shows the gateway configuration:

import boto3 

bedrock_client = boto3.client('bedrock-agentcore-control', region_name='<your-region>') 
# e.g., region_name='us-west-2' 

bedrock_client.update_gateway( 
    gatewayIdentifier='<your-gateway-id>', 
    interceptorConfigurations=[
        { 
            'interceptor': { 
                'lambda': { 
                    'arn': 'arn:aws:lambda:<region>:<account-id>:function:<YourInterceptorFunction>' 
                } 
            }, 
            'interceptionPoints': ['REQUEST'], 
            'inputConfiguration': { 
                'passRequestHeaders': True 
            } 
        } 
    ] 
) 

Step 2: Validate the inbound JWT

The interceptor independently validates the JWT signature as a defense-in-depth measure, protecting against scenarios where the request Lambda interceptor could be invoked through a path that bypasses gateway validation. It fetches the identity provider’s JSON Web Key Set (JWKS) (cached across warm Lambda invocations to avoid repeated network calls), verifies the token’s signature, expiration, and issuer, then returns the decoded claims.

The following code demonstrates JWT validation:

  import jwt 
  from jwt import PyJWKClient 

  COGNITO_ISSUER = 
  f"https://cognito-idp.{COGNITO_REGION}.amazonaws.com/{YOUR_COGNITO_USER_POOL_I 
  D}" 
  jwk_client = PyJWKClient(f"{COGNITO_ISSUER}/.well-known/jwks.json") 

  def validate_jwt(token): 
      """Validate JWT signature and return decoded claims.""" 
      signing_key = jwk_client.get_signing_key_from_jwt(token) 
      return jwt.decode(token, signing_key.key, algorithms=["RS256"], 
  issuer=COGNITO_ISSUER) 

Step 3: Retrieve system credentials from Secrets Manager

The interceptor retrieves the system service account credential from Secrets Manager. This credential authenticates the AI agent to the downstream tool. The secret is encrypted with a customer-managed AWS Key Management Service (AWS KMS) key and cached in memory for the configured time-to-live (TTL) to minimize API calls while ensuring rotated credentials are picked up promptly.

The following code retrieves the credential from Secrets Manager:

  import boto3 
  secrets_client = boto3.client('secretsmanager') 

  def get_system_credentials(): 
      """Retrieve the system service account credential from Secrets Manager.""" 
      response = secrets_client.get_secret_value( 
          SecretId=os.environ['SYSTEM_CREDS_SECRET_NAME'] 
      ) 
      return json.loads(response['SecretString']) 

IAM permissions: The interceptor’s execution role requires secretsmanager:GetSecretValue scoped to the specific secret Amazon Resource Name (ARN), and kms:Decrypt scoped to the KMS key used to encrypt it. Follow the principle of least privilege by restricting the resource ARN rather than using wildcards.

Note: The agent doesn’t have access to Secrets Manager. Only the request Lambda interceptor—a deterministic function not influenced by model behavior—retrieves credentials. This isolation is designed to mitigate the risk of adversarial prompts instructing the model to access or exfiltrate authentication credentials, even if the agent is compromised.

Step 4: Construct the Basic Auth header

The request Lambda interceptor constructs the Basic Auth header using the system credential retrieved for the downstream tool.

The following code shows the core transformation logic.

  def build_system_auth_header(headers): 
      """Validate JWT and construct Basic Auth header with system credential.""" 
      auth_header = headers.get('Authorization', '') 
      if not auth_header.startswith('Bearer '): 
          return _error_response(401, "No Bearer token found in request.") 

      # Validate JWT (defense-in-depth) 
      claims = validate_jwt(auth_header[7:]) 
      if not claims: 
          return _error_response(401, "JWT validation failed.")
          
      # Retrieve system credential from Secrets Manager 
      creds = get_system_credentials()
      
      # Construct Basic Auth header (RFC 7617) 
      basic_auth_encoded = base64.b64encode( 
          f"{creds['username']}:{creds['password']}".encode() 

      ).decode() 
      headers['Authorization'] = f"Basic {basic_auth_encoded}" 
      return headers 

Conclusion

A request Lambda interceptor in Amazon Bedrock AgentCore Gateway can bridge the gap between the authentication patterns supported by the gateway and the authentication requirements of legacy tool APIs that haven’t yet migrated to modern authentication standards. As demonstrated in this post, the interceptor validates the inbound JWT, retrieves system credentials from Secrets Manager, and constructs the downstream tool’s Basic Auth header without modifying tool schemas or agent implementation.

This approach is an interim integration pattern, not a target architecture. It introduces a credential that must be synchronized between Secrets Manager and the tool’s identity store (such as Active Directory), adding operational overhead for rotation, drift detection, and lifecycle management. The recommended path is to modernize the downstream tool to accept OAuth 2.0, SAML, or OpenID Connect, eliminating stored credentials entirely. Until that modernization is complete, the interceptor isolates credential handling from the agent runtime, designed to help ensure that the agent—a non-deterministic system influenced by user prompts—does not have access to authentication secrets.

If you have feedback about this post, submit comments in the Comments section below.


Nashant Mainro

Nishant Mainro

Nishant is a Senior Security Solutions Architect with Amazon Web Services, based in Atlanta, Georgia. He brings 17+ years of security experience, focusing on securing AI and agentic workloads. He enjoys architecting security controls at scale, including identity, authorization, and data access for AI agents, empowering customers to confidently build generative AI applications and protect their data on AWS.

Author

Ram Ramani

Ram is a technology leader in AI security focusing on AI-driven software development, AI for security, and building secure agents. Ram advises leaders, developers and architects on how to make an organization AI-native and secure while benefiting from velocity provided by AI-driven development.

AWS Weekly Roundup: AWS Heroes Summit, Web Search on Amazon Bedrock, Dogwood, Kiro Crew, and more (August 10, 2026)

Post Syndicated from Channy Yun (윤석찬) original https://aws.amazon.com/blogs/aws/aws-weekly-roundup-aws-heroes-summit-web-search-on-amazon-bedrock-dogwood-kiro-crew-and-more-august-10-2026/

Last week, we brought together AWS Heroes from around the world to connect, collaborate, and celebrate the builders who go above and beyond for the AWS community.

The AWS Heroes Summit, an invite-only annual gathering, brings global experts specializing in fields like AI, serverless, and containers together for direct collaboration, technical deep-dives, and feedback sessions with internal AWS product and service teams.

Day 1 started with an inspiring fireside chat from AWS CEO Matt Garman. From an insightful AMA with James Hamilton on Day 2 to breakout sessions from various product teams that sparked new ideas, our AWS Heroes excelled at sharing knowledge, lifting each other up, and turning conversations into collaborations. To learn more, read the attendee feedback on LinkedIn.

Last week’s launches
Here are some launches that got my attention:

  • Web Search on Amazon Bedrock: Amazon Bedrock now enables OpenAI models (GPT-5.4, GPT-5.5, and GPT-5.6 Sol/Terra/Luna) to browse and retrieve information from the internet, allowing AI applications to access up-to-date information beyond their training data. This capability opens new possibilities for building AI agents and applications that can answer questions using real-time web content while maintaining data residency within your secured AWS environment with zero data egress. To get started, visit the AI blog post and the Amazon Bedrock User Guide.
  • Runtime Instances on Amazon Bedrock AgentCore: You can now deploy and run AI agents on dedicated runtime instances through Amazon Bedrock AgentCore, providing more control over agent execution environments with predictable performance and cost. To get started, visit Sébastien’s blog post and AgentCore documentation.
  • Vector search for Amazon DynamoDB: You can store and query vector embeddings alongside your existing data in DynamoDB without managing a separate vector database. DynamoDB already supports storing memory for AI agents, and with vector search you can now add semantic retrieval over that memory for agentic grounding, with predictable performance. To learn more, visit Esra’s blog post and Amazon DynamoDB Developer Guide.
  • AWS Transform continuous modernization now generally available: This capability helps engineering teams analyze and remediate technical debt across source code repositories at scale. You can modernize mainframe and legacy workloads with an ongoing, automated approach rather than a one-time migration event. To learn more, visit Micah’s preview blog post. You can also try the AWS Transform Kiro Power and agent plugins.
  • Up to 3,000 Mbps for AWS Lambda function bandwidth: AWS Lambda functions now support increased network bandwidth, enabling data-intensive workloads and faster communication between Lambda functions and other AWS services. This feature enables functions outside a VPC that are configured with 2 GB of memory or more to access network bandwidth that scales proportionally, from 625 Mbps at 2 GB up to 3,000 Mbps at 10 GB.

For a full list of AWS announcements, be sure to keep an eye on the What’s New with AWS page.

Other AWS news
Here are some additional projects and news items that you may find interesting:

  • Introducing Dogwood: Runtime Verification for AI Agents: AWS open-sourced Dogwood, a purpose-built governance language for AI agents to support Cedar policies and add temporal conditions. Powering Dogwood, Amazon Bedrock AgentCore introduced temporal policies whose decisions depend on the history of an agent’s actions within a session, not on the current request alone.
  • AWS supports Agent Plugins: An Open Standard for Portable Agent Extensions: AWS announced support for Agent Plugins, an open source, vendor-neutral specification that gives AI agent extensions a common packaging format so you can package an extension once and ship it to any client, including Kiro, VS Code, Cursor, or any tool that implements the spec.
  • Introducing Kiro Crew: Kiro Crew is a persistent, self-evolving workspace that keeps work moving, online or off, enabling collaborative multi-agent development workflows within the Kiro IDE. It’s built for engineering work that goes beyond a single chat session, and spans repos, tools, and days. You can run several efforts in parallel or hand work to subagents that report back, so nothing waits in line.

For a full list of AWS blog posts, be sure to keep an eye on the AWS Blogs page.

Learn more about AWS, browse and join upcoming AWS-led in-person and virtual events, startup events, and developer-focused events including AWS Summits and AWS Community Days. Join the AWS Builder Center to connect with builders, share solutions, and access content that supports your development.

That is all for this week. Check back next Monday for another Weekly Roundup!

— Channy

Runtime instances: persistent compute for production AI agents on Amazon Bedrock AgentCore

Post Syndicated from Sébastien Stormacq original https://aws.amazon.com/blogs/aws/runtime-instances-persistent-compute-for-production-ai-agents-on-amazon-bedrock-agentcore/

When you move AI agents from prototype to production, the infrastructure challenges multiply. Your agents need to persist state across multi-step workflows that run for hours or days. They need to coordinate with other agents, share context, and sometimes access GPUs for specialized tasks. Amazon Bedrock AgentCore runtime microVMs provide a fully managed environment for invocations that can run for up to 8 hours and support stateful workflows through managed session storage. Some workloads also benefit from dedicated, larger-capacity environments — for example, when agents need to run continuously for multiple days, access GPUs or the underlying OS, or run multiple collaborating agents on the same host.

Today, I’m happy to announce runtime instances, a new complementary compute option in Amazon Bedrock AgentCore Runtime that gives your agents persistent, managed infrastructure purpose-built for complex agent workloads.

What you get
Runtime instances provides AWS-managed EC2 infrastructure where you deploy multiple agents in a single runtime, each with their own dependencies and artifact types. Your agents can collaborate on the same host within shared sessions that persist for up to 14 days. The service supports GPU acceleration for compute-intensive tasks, session stop/restart to save costs during idle periods, and containerized deployments for teams that want to ship independently. For knowledge that needs to survive beyond a session, runtime instances pairs naturally with Amazon Elastic Block Store (Amazon EBS) and AgentCore Memory, which gives your agents long-term recall across sessions and environments.

Before today, if you wanted to keep your agents running for days or they needed GPU access, or multi-agent coordination, you had to build and manage that infrastructure yourself. You provisioned EC2 instances, configured networking, set up session management, handled scaling, and stitched together monitoring. Runtime instances handles all of that for you while integrating with the same AgentCore APIs, identity controls, and observability you already use with AgentCore Runtime microVMs.

A few things that should make agent developers smile: your agents can call each other as tools within a shared session, iterating autonomously until the job is done. You bring any framework (CrewAI, LangGraph, LlamaIndex, Strands) and any model. Packaging is minimal, a @app.entrypoint decorator and a zip file or container image. And if your workflow spans days, hibernate Monday night and resume Wednesday morning with everything intact.

Runtime microVMs and runtime instances are complementary compute options that you can use independently or together through the same AgentCore runtime APIs. A lightweight orchestrator agent on runtime microVM can coordinate and dispatch work to specialized worker agents running on instances. The orchestrator handles API calls, task routing, and result aggregation using runtime microVM’s fast scaling, while workers on Instances perform compute-intensive tasks like code compilation, security scanning, or GUI automation that require persistent state and direct OS access.

Let me show you how it works
I built two agents for this demo: a code writer agent that generates Python code from natural language descriptions, and a code reviewer agent that analyzes the generated code for bugs, security issues, and style improvements. Both agents share the same file system, so the reviewer can read whatever the writer produces without any data transfer or API calls between them.

Here is the code writer (simplified, no error handling):

writer = Agent(
    model="us.anthropic.claude-sonnet-4-5-20250929-v1:0",
    system_prompt=(
        "You are a senior Python engineer. "
        "Given a task, return ONLY a single Python code block — no prose."
    ),
)

@app.entrypoint
def handler(event, context):
    task = event.get("task") or event.get("prompt")
    session_id = getattr(context, "session_id", None) or event.get("session_id")
    session_dir = SHARED_DIR / session_id
    session_dir.mkdir(parents=True, exist_ok=True)

    code = str(writer(task))
    (session_dir / "code.py").write_text(code)

    return {"agent": "writer", "wrote": str(session_dir / "code.py"), "code": code}

Here is the code reviewer agent (simplified, no error handling):

reviewer = Agent(
    model="us.anthropic.claude-sonnet-4-5-20250929-v1:0",
    system_prompt=(
        "You are a strict Python code reviewer. "
        "Given code, return 3 bullet points: bugs, style, suggestions."
    ),
)

@app.entrypoint
def handler(event, context):
    session_id = getattr(context, "session_id", None) or event.get("session_id")
    code_path = SHARED_DIR / session_id / "code.py"
    code = code_path.read_text()
    review = str(reviewer(f"Review this code:\n\n{code}"))

    return {"agent": "reviewer", "read": str(code_path), "review": review}

Each agent is a Python application using Strands Agents with an @app.entrypoint decorator and a model of its choice. I package each one as a zip file. For this demo, I use the AWS Management Console. You can also use the AgentCore CLI, the AWS Command Line Interface (AWS CLI) or infrastructure as code.

Step 1: Create a capacity provider.

A capacity provider defines the EC2 infrastructure your agents run on. In the AgentCore console, I select Runtime in the left navigation, then select the Capacity providers tab and Create capacity provider.

ACI Create Capcity Provider 1

I give it a Name, select Linux (64-bit ARM) as the Operating system, and choose c7g.2xlarge as the Allowed instance types. This gives me 8 vCPUs and 16 GiB of memory, enough for both agents to run comfortably side by side.

Further down, I configure the VPC, subnets, and security groups for network access. Under Storage configuration, I keep the default gp3 volume. Under Service access, I select Create a new service role and let the console create the infrastructure role that manages EC2 instances on my behalf.

I select Create capacity provider and wait a few seconds. The status moves to Active.

ACI Create Capacity Provider 2

ACI Create Capacity Provider 3

Note the capacity provider configuration summary: operating system, instance type, subnets, security group, instance profile, and infrastructure role. Once created, only the description can be edited, so verify your settings before you proceed.

ACI Create Capcity Provider 2

Step 2: Create a runtime and deploy the first agent.

Back on the Runtime page, I select Create runtime. I give it a Name, select Instances as the Compute type, and choose the Capacity provider I created in the previous step.

ACI Create Runtime 1

Under Agent source, I select S3 Source, then Upload to S3. I choose my agent zip file (ACIDemoWriter.zip), set the Language runtime to Python 3.13, and specify agent.py as the Agent entry point. This is the file that contains my @app.entrypoint decorated function. Under Permissions, I select Create default role to let the console provision the IAM role my agent needs.

ACI Create Runtime 2

I select Create runtime and wait for the status to become Ready.

I repeat the same process for my code reviewer agent. I create a second runtime, select the same capacity provider, upload my reviewer agent zip file, and wait for it to become Ready. Both agents now share the same underlying EC2 infrastructure.

AgentCore Runtime Instances - Agent ReadyThe console shows me a View invocation code section with ready-to-use Python, TypeScript, and JavaScript snippets to invoke my agent programmatically. But for this demo, I use the built-in test feature. I select Test on the writer agent’s page.

AgentCore Runtime Instances - Show invocation codeStep 3: Invoke agents and observe collaboration.

The Runtime playground opens. At the top, I see three fields: Runtime agent, Endpoint, and Session ID. The console generates a session ID automatically. I take note of it because I will reuse it with the reviewer agent.

In the Input field, I type a JSON payload asking the writer agent to generate code:

{"prompt": "write a fibonacci suite"}

I select Run. After a few seconds, the Output panel shows the agent’s response. The writer agent generated a Python module with two implementations of a Fibonacci sequence (a list-based function and a generator) and wrote it to /tmp/agentcore-session/ca5ec24d-07f5-4eeb-add1-5ba416bf9eb2/code.py. Notice the session ID in the file path. That directory is the shared file system for this session.

AgentCore Runtime Instances - Invoke code writer agent

Step 4: Invoke the reviewer agent in the same session.

Now I switch the Runtime agent dropdown to ACIDemoReviewer. The important part: I paste the same session ID (ca5ec24d-07f5-4eeb-add1-5ba416bf9eb2) in the Session ID field. This is what connects the two agents.

I type a simple prompt:

{"prompt": "review the code"}

I select Run. The reviewer agent reads the file the writer produced from the shared session directory and returns a detailed code review. It finds no critical bugs but suggests adding type hints, input validation, and simplifying the edge case handling.

AgentCore Runtime Instances - Invoke code reviewer agentThe two agents never exchanged messages or called each other’s APIs. They collaborated through the shared file system that runtime instances provide within a session. You can extend this pattern to any number of agents: a test agent that runs the code, a documentation agent that generates README files, a security agent that scans for vulnerabilities, all sharing the same working directory.

Key details
Here are a few things to know as you get started:

  • Supported OS: Linux (ARM64 and x86_64) at launch.
  • Session persistence: Sessions persist for up to 14 days.
  • Runtimes: Python 3.11-14 with native code support. Container images also supported.
  • GPU: Support for GPU-accelerated instance types.
  • Integration: Uses the same AgentCore APIs, identity, observability, and policy controls as AgentCore Runtime.
  • Pricing: Standard EC2 pricing plus a management fee for AgentCore orchestration.
  • Regions: US East (Ohio, N. Virginia), US West (Oregon), Asia Pacific (Mumbai, Singapore, Sydney, Tokyo), and Europe (Frankfurt, Ireland)

To get started, visit the runtime instance in Amazon Bedrock AgentCore documentation and create your first capacity provider.

— seb

AWS Weekly Roundup: Local Zone in Athens, Claude Opus 5 on AWS, Lambda durable execution for .NET, and more (July 27, 2026)

Post Syndicated from Daniel Abib original https://aws.amazon.com/blogs/aws/aws-weekly-roundup-july-27-2026/

Last week I had the privilege of spending three days in São Paulo with technical builders from across Latin America, brought together for a regional tech event full of deep-dive sessions, hands-on workshops, and conversations with customers and partners. What struck me most wasn’t any single session, it was the energy of a technical community that so rarely gets to be in the same room. People traded architecture ideas over coffee, sketched out solutions on whiteboards, and left with a longer list of things to try than they arrived with. It’s a good reminder that, for all the tooling we build, the community around it is what makes the technology stick.

That community spirit connects nicely to the week’s biggest infrastructure news, which is all about bringing AWS closer to where builders actually are.

Now, let’s get into this week’s AWS news…

Headlines
AWS Local Zone in Athens, Greece: AWS has opened a new Local Zone in Athens, Greece, the second Local Zone in EMEA with support for Amazon S3 and Amazon EBS Local Snapshots, so you can store and process data within Greece to help meet local data residency requirements. The Athens Local Zone supports Amazon EC2 (C7i, M7i, and R7i instances), Amazon S3 with the One Zone-Infrequent Access storage class, Amazon EBS, and Amazon ECS.

Athens, Greece skyline

AWS Local Zones place AWS infrastructure much closer to large population and industry hubs, enabling applications that require single-digit millisecond latency, such as real-time gaming, media production, and financial services, to run where end users actually are. For builders in Greece, you can now run latency-sensitive workloads locally while connecting seamlessly to the nearest AWS Region for services that don’t require low latency, giving you the flexibility to architect hybrid, latency-optimized applications without managing your own data center infrastructure. To learn more, visit AWS Global Infrastructure and Sustainability Blog post.

Last week’s launches
Here are some launches and updates from this past week that caught my attention:

  • Claude Opus 5 on AWS: You can use Anthropic’s Claude Opus 5, the most advanced Opus model yet, matching Claude Fable 5’s top-tier intelligence in many domains at Opus-tier pricing. Amazon Bedrock offers Claude Opus 5 with zero data retention (ZDR) enabled by default, giving you Opus’ top-tier intelligence while meeting your data governance requirements unlike Claude Fable 5. You have two ways to access Claude Opus 5: Amazon Bedrock and Claude Platform on AWS. To learn more, visit the deep dive blog post.
  • AWS Lambda durable execution SDK for .NET is now generally available: You can now build resilient, long-running workflows in C# using Lambda durable functions, without implementing custom progress tracking or integrating an external orchestration service. The SDK is a natural fit for multi-step applications like payment processing pipelines, AI agent orchestration, and human-in-the-loop approvals, it checkpoints progress automatically and can pause execution for up to a year. If you’re a .NET developer building serverless workflows, this removes a lot of the plumbing you used to write by hand.
  • Amazon Bedrock AgentCore now delivers unified observability with traces and logs in a single log group: Amazon Bedrock AgentCore now delivers agent traces and prompts to the same Amazon CloudWatch log group as your agent’s logs. Previously, telemetry was split across destinations, trace spans went to a shared log group while prompts, inputs, and outputs went to a separate one, so debugging a single agent invocation meant searching in multiple places. You can now debug an invocation in one place, and apply fine-grained access control and customer-managed key (CMK) encryption at the individual agent level.
  • Amazon Connect delivers more natural agentic voice experiences: Amazon Connect now supports more natural, human-sounding agentic voice experiences across 50+ languages, including Portuguese, Spanish, French, Italian, Japanese, Korean, and Thai, with over 100 new voice options and conversational improvements that make AI interactions sound more fluid. Connect’s agentic self-service lets AI agents understand, reason, and take action across voice and digital channels, adapting to a customer’s tone and sentiment. You can now build contact center experiences that feel natural to callers in far more of the languages your customers actually speak.
  • Amazon SageMaker Unified Studio now supports Amazon OpenSearch: You can now query and analyze your search and log analytics data from Amazon OpenSearch directly alongside other data assets in Amazon SageMaker Unified Studio. With this connection, you can combine operational search data in OpenSearch with data from sources like Amazon Redshift, Amazon S3, and relational databases, all within a single, governed environment. It’s especially useful when you need to correlate analytical and operational workloads, such as joining application logs with transactional data to uncover insights.
  • Amazon CloudWatch announces coding agent insights: Amazon CloudWatch now gives engineering leaders visibility into how AI coding tools are driving value across their organization. Coding agent insights integrates with the Claude apps gateway for AWS to collect telemetry from Claude Code without additional instrumentation, and also supports agents like Codex and GitHub Copilot. As teams scale AI coding adoption, you can now measure the return on that investment with metrics built on OpenTelemetry, no custom instrumentation required.

For a full list of AWS announcements, be sure to keep an eye on the What’s New with AWS page.

Other AWS news
Here are some additional posts and resources that you might find interesting:

Upcoming AWS events
Check your calendar and sign up for upcoming AWS events:

  • AWS Summits: AWS Summits are free events that bring the cloud and AI community together to connect, learn, and explore the latest technologies. Browse the full calendar to find a Summit near you in the second half of 2026.
  • AWS Community Days: Community-led conferences where content is planned, sourced, and delivered by community leaders. If you’re in Latin America, don’t miss AWS Community Day Belo Horizonte on August 22, registration is open at awscommunityday.com.br.

Join the AWS Builder Center to connect with builders, share solutions, and access content that supports your development. Browse here for upcoming AWS-led in-person and virtual events and developer-focused events.

That’s all for this week. Check back next Monday for another Weekly Roundup!

This post is part of our Weekly Roundup series. Check back each week for a quick roundup of interesting news and announcements from AWS!

Multi-cloud lakehouse architecture on AWS for Agentic AI, Part 1: Architecture and best practices

Post Syndicated from Sakti Mishra original https://aws.amazon.com/blogs/big-data/multi-cloud-lakehouse-architecture-on-aws-for-agentic-ai-part-1-architecture-and-best-practices/

Enterprise data architectures have become fundamentally distributed. Over the past decade, organizations have made deliberate investments across multiple platforms such as relational databases for transactional workloads, cloud data warehouses for analytics, object stores for unstructured data, and SaaS applications for domain-specific functions. Each was chosen to solve a specific problem, serve a specific team, or meet a specific performance requirement. The result is not accidental sprawl. It is a deeply heterogeneous data landscape shaped by intentional, workload-driven decisions. The challenge now is not consolidation, but interoperability: enabling these systems to function as a unified foundation for the next generation of AI-driven applications.

Agentic AI systems that autonomously reason, plan, and take action on behalf of users are moving rapidly from experimentation to enterprise production. These systems do not just retrieve information. They synthesize it, act on it, and learn from it. And unlike traditional analytics tools that can work with a well-scoped dataset, AI agents require something more demanding: unified, governed, and real-time access to all relevant enterprise data, regardless of where it lives.

This is the gap that matters most right now. Enterprises that have invested in building strong data capabilities across multiple providers are well-positioned, but only if those platforms can be accessed together, consistently, and with the governance controls that enterprise AI requires. Without a unified data foundation, AI agents operate with incomplete context, governance becomes inconsistent, and the promise of autonomous AI remains out of reach.

Solution approach

The following high-level architecture explains how you can onboard metadata catalogs and MCP servers to your context layer, which becomes the primary input for your AI agents.

Assuming your data products have a well-defined metadata catalog, you can take a unified-catalog-first approach, then build the context layer on top of it to let your AI agents discover all the context from one place. This helps bring in centralized governance and audit control, because every request gets routed through the centralized metadata catalog and context layer to simplify implementation of unified governance. In addition, this brings simplicity to enable business semantics, define attribute priorities, and define authoritative sources for the consumer use cases.

Architecture showing metadata catalogs and MCP servers onboarded to a context layer that feeds AI agents

If any of the data sources does not have a well-defined metadata catalog, you can define Model Context Protocol (MCP) servers on them, and then directly onboard them to the context layer. For example, if you have semi-structured or unstructured datasets for which you do not have a well-defined metadata catalog, or you want to onboard third-party data sources through REST APIs, then you can add their respective MCP server to the context layer directly. The following architecture explains the extended flow for it.

Extended architecture where data sources without a metadata catalog expose MCP servers directly to the context layer

In this series of posts, we demonstrate how you can unify the metadata catalog access across multiple providers, how you can enable AI agents to query the unified catalog, and how the context layer can be integrated to unify metadata from catalogs and MCP servers. We have divided the series into the following parts.

  • Part 1: Architecture approach with tradeoffs to unify a multi-cloud lakehouse architecture that can power Agentic AI (this post).
  • Part 2: Implementing an example solution to unify catalogs from multiple providers and deploy AI agents to query the unified data access layer.
  • Part 3: Integrate a context layer on top of the unified catalog for AI agents.
  • Part 4: Onboard additional data sources to the context layer through MCP servers and demonstrate the full solution.

This post focuses on explaining the architecture approach to build the open lakehouse architecture on AWS, unifying the metadata catalog across providers for the AI agents to access. In addition, it highlights the architecture trade-offs and best practices.

Use case

Every AI initiative launched on a fragmented data foundation is an initiative that will need to be rebuilt. Organizations that establish unified data access today are the ones that will scale Agentic AI with confidence tomorrow. Consider a large enterprise managing petabytes of data across a diverse set of environments:

  • On-premises: Network device telemetry, customer records, and operational databases.
  • Multiple cloud platforms: Marketing analytics, HR systems, and enterprise applications distributed across cloud providers.
  • Data platforms: Data science workloads, feature engineering pipelines, and finance and supply chain analytics running on specialized platforms.
  • SaaS applications: Salesforce, SAP, Zendesk, ITSM, and other business tools that each hold a critical piece of the enterprise data picture.

The business objective is to build a unified analytics and AI platform that can:

  • Query and analyze data across all environments without requiring full data migration.
  • Enforce consistent data governance and access control regardless of data location.
  • Power AI agents that can autonomously discover, query, and act on enterprise data.
  • Reduce total cost of ownership by eliminating redundant pipelines and storage.

This architecture directly addresses these needs by combining flexible data integration patterns, an open-table-format-based lakehouse architecture (with an example of Apache Iceberg), AI agent deployment to access unified metadata, and centralized governance.

Reference architecture

Before going deeper into a specific architecture, let’s revisit at a high level how the AWS open lakehouse architecture enables data ingestion and query or catalog federation to power analytics, machine learning development, and generative AI application development.

The following architecture diagram represents an end-to-end flow that includes:

  • Data ingestion to the data lake or data warehouse through Zero-ETL and batch or stream processing using AWS native services, or accessing data from Google Cloud Platform using AWS Interconnect – multicloud.
  • A centralized metadata catalog layer that includes data on AWS and metadata representation of non-AWS data sources using query or catalog federation.
  • A context layer that you can integrate to create a knowledge graph with ontology and business semantics that can enrich context for AI agents.
  • The consumption layer, which can include analytics, machine learning model development with Amazon SageMaker AI, and generative AI application development with Amazon Bedrock AgentCore, Amazon Quick, or other AWS and non-AWS AI applications.

End-to-end AWS open lakehouse architecture spanning ingestion, catalog, context, and consumption layers

Let’s look at an expanded version of this architecture that details the data ingestion and data consumption patterns to build a unified data access layer on AWS that spans multiple cloud and ISV providers.

Expanded technical architecture walkthrough

The following architecture demonstrates the comprehensive AWS approach for metadata catalog consolidation through flexible integration patterns, and it also highlights patterns for building a lakehouse on AWS. Built on the open standards of Apache Iceberg for storage and governance through AWS Lake Formation, it creates a unified data foundation that connects existing investments without requiring wholesale migration, and it makes enterprise data AI-ready from day one. This architecture delivers value at every layer: business teams query across platforms without data movement, IT teams manage governance through a single federated layer with the flexibility to federate or ingest per use case, and compliance teams enforce policies once across all sources with full lineage and audit coverage.

Expanded lakehouse architecture on AWS showing federation and ingestion patterns across multiple cloud and ISV providers

The following are the key components of the architecture.

Data access methods

This section provides options to access data that is not available in AWS Glue Data Catalog and not available on AWS.

1. Iceberg catalog federation (Reference points 2, 6.1, 6.2)

  • AWS Glue Data Catalog implements the Iceberg REST Catalog API specification, which enables seamless federation with Databricks, Snowflake, or other Iceberg-compatible catalogs set up with Amazon Simple Storage Service (Amazon S3) as the storage layer.
  • With the growing adoption of Apache Iceberg, catalog federation will become a common standard in the future and simplify metadata unification.

2. Query federation (Reference point 1.1)

  • Direct cross-cloud querying over the public internet to Google BigQuery, Azure SQL, Salesforce, and other platforms.
  • Real-time access to external data sources without replication, and seamless access with AWS analytics services.
  • Provides flexibility, because the catalog federation capability of the Iceberg REST catalog is limited to Iceberg tables only.

2.1. Secured private connectivity to Google Cloud Platform using AWS Interconnect for multi-cloud (Reference points 3.1, 3.2)

The default query federation approach makes the connection and transfers data over the public internet, which has its own latency implications depending on the target platform and the data volume transferred over the internet. During re:Invent 2025, AWS announced the public preview of AWS Interconnect – multicloud, which recently became generally available.

AWS Interconnect – multicloud is a managed service that provides private, high-speed, and secure network connections between Amazon Web Services (AWS) and other cloud providers, starting with Google Cloud Platform (GCP), with Microsoft Azure and Oracle Cloud Infrastructure (OCI) coming later in 2026. You can enable the integration with three steps: 1) specify the target cloud service provider, 2) select the destination Region on the other side, and 3) pick the required bandwidth.

The following architecture represents AWS and GCP integration with AWS Interconnect – multicloud.

High-level architecture of AWS and GCP integration through AWS Interconnect for multi-cloud

On the AWS side, you need an AWS Direct Connect gateway (a global construct that acts as a route reflector), which you can attach to your Amazon Virtual Private Cloud (Amazon VPC) through a virtual private gateway or AWS Transit Gateway, or AWS Cloud WAN. On the GCP side, you need a Google Cloud Router that you attach to your customer VPC. Interconnect – multicloud offers pre-cabled capacity pools at shared Interconnect points of presence (PoPs) in selected Regions, where both AWS and GCP routers are co-located and pre-wired.

Because Interconnect – multicloud primarily routes traffic within the VPC through a private network, to benefit from it you need to keep your query engine or jobs within a customer VPC.

2.2. High network bandwidth with on-premises systems (Reference point 4)

  • AWS Direct Connect for high-bandwidth, low-latency on-premises connectivity.

Data ingestion methods

This section focuses on ways you can use to onboard datasets (complete or subset) to a lakehouse on AWS.

1. Zero-ETL: Data movement to AWS with Zero-ETL ingestion (Reference points 5.1, 5.2)

  • AWS Zero-ETL capabilities for seamless data loading from AWS and non-AWS sources.
  • Flexibility to choose your target as an Amazon S3 based data lake or Amazon Redshift.

2. Extract, transform, load (ETL): Extract data from JDBC or SaaS sources and transform through a batch or stream pipeline (Reference points 3.1, 3.2)

The following architecture expands the flow 1.1 to 1.2 ingestion method that integrates AWS services to onboard data to the Amazon S3 raw layer and then takes it through an ETL pipeline for data cleansing and transformations. It also includes steps to onboard unstructured data to Amazon S3 using Amazon Bedrock Data Automation, and taking the lakehouse data for machine learning development with Amazon SageMaker AI.

Ingestion architecture integrating AWS services to load data into the Amazon S3 raw layer and process it through an ETL pipeline

You can also use AWS Interconnect – multicloud to run Spark jobs (Spark with Amazon EMR on EKS or open source Spark on any compute within a customer VPC) to ingest and transform data from Google Cloud with private connectivity.

3. Accessing data from Google Cloud over a private network

Refer to the preceding data access methods (3.1 and 3.2).

4. Onboarding data from AWS Outposts (S3 on Outposts) (Reference points 9.1 to 9.5)

  • Option to onboard S3 on AWS Outposts data to regional Amazon S3 through AWS DataSync (reference 9.1 to 9.3), which might be a better fit to sync files as-is through a scheduled batch or an event-driven approach.
  • Flexibility to transform the S3 on Outposts data using an Amazon EMR clusters on Outposts job, and then directly write the transformed output to a regional Amazon S3 bucket in the formats you want (including open table formats such as Apache Hudi, Apache Iceberg, and Delta Lake).

Lakehouse foundation with Apache Iceberg

By standardizing on Apache Iceberg, you’re not choosing AWS over your other platforms. You’re choosing interoperability and future flexibility. Your data becomes truly portable across any Iceberg-compatible engine.

  • Open table format: Industry-standard format supported across AWS, Databricks, Snowflake, and other platforms, which eliminates vendor lock-in.
  • ACID transactions: Reliability with full transactional consistency.
  • Time travel and schema evolution: Built-in versioning and flexible schema management.
  • Performance optimization: Advanced features such as hidden partitioning, partition evolution, and metadata management.

Note that lakehouse storage is not limited to the Apache Iceberg format, and you have the flexibility to include other open table formats (for example, Apache Hudi and Delta Lake) or file formats (for example, Apache Parquet and Apache Avro).

Unified governance and access control

AWS governance capabilities transform the lakehouse from a storage layer into a fully governed data platform. This delivers security, compliance, and data quality out of the box, applied consistently across all data sources including federated catalogs. A unified catalog consolidates metadata from AWS and non-AWS sources with generative AI-powered business glossary generation, while automated ML-powered classification identifies sensitive data (for example, PII, PHI, and financial data) across structured and unstructured datasets. AWS Identity and Access Management (AWS IAM) and AWS Lake Formation enforce fine-grained access control at the row, column, cell, and tag level, applied consistently across Amazon Athena, Amazon Redshift Spectrum, Amazon EMR, and federated sources. End-to-end data lineage tracking provides visual data flow graphs, impact analysis, and compliance audit trails. When AI agents explore metadata from the unified catalog and submit a query to Amazon Athena for execution, the Lake Formation fine-grained access control filters data based on the user interacting with the AI agent.

For the foundation model integrated into your AI agents, you can use Amazon Bedrock Guardrails, which implements customized safeguards to block harmful content and minimize hallucinations. Amazon Bedrock AgentCore provides fine-grained policy control over agent actions with real-time enforcement and managed authentication for agents accessing AWS and third-party services.

A comprehensive audit and compliance stack spans Amazon CloudWatch, AWS CloudTrail, AWS IAM, AWS Key Management Service (AWS KMS), AWS Audit Manager, and AWS PrivateLink. This stack makes sure every agent invocation is traceable, every key is managed, and every configuration is automatically mapped to frameworks including ISO, SOC, GDPR, and HIPAA.

When an end user interacts with the AI chat assistant, the layers of security and governance should go through the following.

Layer 1: Who can access?

  • Enable Active Directory and single sign-on integration for user authentication, and a combination of AWS IAM roles for AWS API-level authorization.

Layer 2: What can they see?

  • Integrate an agent profile to define what datasets each agent can access, because not all agents should have access to all datasets.
  • Enable fine-grained access control on the metadata layer using AWS Lake Formation that can filter rows and columns.
  • Enable data masking as applicable while the query responses are served through the query engine.

Layer 3: What can the agent do?

  • Control agent actions by restricting them to read-only, and apply restrictions to INSERT, UPDATE, and DELETE if the agents are supposed to query only.
  • Apply a limit on the number of rows that can be returned from the query, and apply a query scan limit to reduce cost.

Layer 4: What does the agent reveal?

  • Enable output filtering to make sure no PII is included.
  • Apply Amazon Bedrock Guardrails on large language model (LLM) responses to make sure the model does not produce anything inappropriate.
  • In addition, enable audit logging of all queries to make sure future audit and compliance needs can be met.

Comprehensive analytics ecosystem (Reference points 7.1, 7.2, 7.3)

AWS offers a complete analytics ecosystem that includes the following.

  • Amazon Athena: Serverless SQL queries with Iceberg v2 support, including provisioned capacity for consistent performance and workgroups for resource and cost management.
  • Amazon Redshift Spectrum: Federated queries across the data warehouse and Iceberg data lake.
  • Amazon Quick Sight: Enterprise visualization with governed access to all data.
  • AWS Glue and Amazon EMR: Distributed data processing capability for enterprise transformations.

AI-ready architecture (Reference points 8.1 to 8.4)

A consolidated lakehouse architecture helps you make data ready for AI agents that can access the data through readily available MCP servers or through the AWS SDK for Python (Boto3) for Amazon Athena or Amazon Redshift Spectrum. AI agents can integrate the AWS MCP Server to interact with AWS analytics services such as AWS Glue, Amazon Athena, and Amazon S3 Tables, a capability of Amazon S3, to query both data and metadata.

AI agents need context to understand how the catalog tables and their attributes are linked to each other, how users have queried them in the past, or what priorities are defined to understand which one is an authoritative source for a particular natural language question. To enable the AI agent with additional context, we can integrate the AWS Context service that was pre-announced recently at the AWS New York Summit 2026.

Governance integration: AI agents automatically inherit Lake Formation permissions, because the agent can submit the SQL query to be run through Amazon Athena or Amazon Redshift Spectrum. This makes sure they only access data that users are authorized to see. Amazon SageMaker Unified Studio data lineage tracks AI agent queries for full auditability.

The following diagram represents how the AI agent request flow looks.

AI agent request flow through the unified catalog, Lake Formation governance, and Amazon Athena

This architecture delivers value across every layer of the organization. Business teams gain faster time-to-insight by querying data across all platforms without waiting for data movement, while eliminating duplicate storage and reducing transfer costs through federation. The Apache Iceberg open table format ensures data portability and freedom from vendor lock-in. For IT and data teams, a single governance layer across all sources, including federated catalogs, reduces operational complexity, while the flexibility to choose between federation and ingestion for each use case, combined with the elastic AWS infrastructure and the petabyte-scale metadata architecture of Iceberg, delivers both agility and scalability. Data governance and compliance teams benefit from a single point of policy enforcement across all data regardless of location, complete lineage and access logs for audit and compliance reporting, automated sensitive data classification, and policies that are defined once and enforced everywhere, including across federated sources.

Architecture tradeoffs and best practices

The following are a few key trade-offs you need to consider while designing the solution.

Data ingestion and access methods

Use catalog federation (Iceberg REST) when:

  • The source platform supports the Iceberg REST API (Databricks, Snowflake Polaris).
  • Data is already in Iceberg format with Amazon S3 backed storage.
  • You want bidirectional discovery (AWS tables visible in Databricks or Snowflake too).

Use query federation (Amazon SageMaker Lakehouse architecture or AWS Glue connectors) when:

  • The source is BigQuery, SQL Server, or another non-Iceberg platform.
  • Data must stay in the source cloud (sovereignty, contractual, or latency reasons).
  • Real-time access is required without replication lag.

Use ingestion (Zero-ETL, AWS Glue, or Amazon EMR) when:

  • Data is accessed frequently with a low-latency requirement by AI agents or high-concurrency analytics.
  • The business decides to build a data lake and warehouse on AWS.
  • You need full governance, time travel, and performance optimization.

Use AWS Interconnect – multicloud when:

  • You need real-time or near-real-time query federation to GCP data sources (BigQuery, AlloyDB, Cloud Spanner) and latency or security requirements prohibit public internet routing.
  • You have high-volume, recurring data transfers between AWS and GCP where public internet egress costs or bandwidth variability are unacceptable.
  • Your organization has compliance or regulatory requirements mandating that data never traverse the public internet (HIPAA, PCI-DSS, or financial services regulations).
  • You need bidirectional connectivity, such as GCP workloads calling AWS APIs, or AWS workloads calling GCP APIs, both over private paths.

Choosing between federation and ingestion based on use case

Dimension Federation (Query in Place) Ingestion (Move to AWS)
Data freshness Real-time or near-real-time Dependent on ingestion frequency
Query performance Subject to source system latency and network Subject to data volume and operation, avoids cross-cloud network latency
Cost Lower storage cost. Higher per-query cost for cross-cloud egress Higher upfront ingestion cost. Lower ongoing query cost
Governance Partial. Source system retains some control, and a unified catalog can simplify governance for consumers Full. Lake Formation enforces all policies across all AWS analytics services
Data portability Data remains in source Data fully portable in open format
AI readiness Limited. Agents depend on source availability High. Agents query optimized, governed Iceberg tables
Operational complexity Lower initial setup. Harder to debug cross-cloud issues Higher initial setup. Simpler long-term operations

Integrating Amazon Bedrock AgentCore Gateway and Amazon Bedrock AgentCore Runtime based on use case

The following are key differences between AgentCore Gateway and AgentCore Runtime that are relevant for our use case.

Dimension Amazon Bedrock AgentCore Gateway Amazon Bedrock AgentCore Runtime
Timeout 5 minutes (hard limit) 15 min sync / 8 hours async
Statefulness Stateless (per-request) Stateful (session-based)
Best for Lightweight API proxying Long-running data processing
Your lakehouse queries Will time out frequently Handles multi-hour jobs

Because AgentCore Gateway has a 5-minute hard timeout limit, use AgentCore Runtime for data processing jobs.

  • AWS Glue ETL jobs can run for minutes to hours.
  • Amazon Redshift queries on large datasets routinely exceed 5 minutes.
  • Athena federated queries (especially cross-cloud through Interconnect) can be slow.
  • Iceberg table scans on multi-TB datasets take time.

You can use AgentCore Gateway if the scope is limited to Glue Data Catalog interactions to fetch metadata schema, because that won’t run for more than 5 minutes.

Design considerations for production implementation

In practice, there are multiple aspects to consider when deploying the solution for production. The following summarizes a few of the key issues you might encounter and approaches to address them.

Catalog federation: The metadata drift problem

One of the first surprises in production is metadata drift, the state where your federated catalog no longer reflects the actual schema of the source system, because the source system’s metadata changes are not reflected in the unified catalog. The agent continues to generate SQL against the stale schema, producing silent failures that are hard to trace.

The following are a few ways you can address the metadata drift issue.

  • Implement a catalog refresh schedule. Even a daily Glue crawler run against federated sources catches most drift before it causes agent failures.
  • Add schema validation as a pre-query step in your agent tool. Before running SQL, verify that the referenced columns exist in the current catalog metadata.
  • Instead of pulling metadata changes from the source in a scheduled manner, you can design an event-driven system, where the source system triggers a push event to run the schema change in the federated catalog.

Query federation: Latency is non-deterministic

Query federation works well for moderate data volumes, but latency becomes non-deterministic at scale. A query that returns in 3 seconds during testing can take more than 10 seconds in production when the source system is under load, the network path is congested, or the federated connector is cold-starting.

The following are a few approaches you can consider to improve the performance.

  • Set explicit query timeouts in your Athena execution context. Without them, a slow federated query will block your agent indefinitely.
  • Implement query result caching for frequently asked questions. Most business users ask the same questions repeatedly, and caching at the agent layer improves perceived performance.
  • For time-sensitive use cases, consider caching aggregated data in an AWS lakehouse on a schedule rather than querying live. This trades freshness for reliability.

AgentCore memory: Statefulness cost

AgentCore Memory enables stateful conversations, but in production, unbounded memory accumulation creates its own problems. An agent that remembers every conversation eventually starts surfacing stale context. For example, a user who asked about Q3 revenue six months ago gets that context injected into a Q1 query today.

The following are a few ways you can optimize cost and improve relevance.

  • Set explicit memory expiry (we use 30 days as shown in the implementation) and enforce it consistently.
  • Use session-scoped memory for transactional queries and long-term memory only for user preferences and recurring patterns.
  • Implement a memory review step in your LangGraph workflow. Before invoking the model, filter retrieved memories by recency and relevance score rather than injecting all of them.

LangGraph orchestration: When tool calls loop

The conditional routing of LangGraph is powerful, but in production we observed a failure mode where the agent enters a tool call loop. The model repeatedly calls the same tool with slightly different parameters, never reaching a satisfactory answer. This typically happens when the tool returns partial or ambiguous results and the model keeps trying to refine.

What we learned:

  • Add a maximum tool call counter in your LangGraph state. If the agent has called tools more than N times in a single session, force a graceful exit with a summary of what was found.
  • Return structured, unambiguous responses from your tools. Include row counts, column names, and explicit null indicators so the model can reason clearly about completeness.
  • Log every tool invocation with its input and output. This is the single most valuable debugging artifact when diagnosing agent misbehavior in production.

Handling hallucination risks in federated agent architectures

This is the most important section for teams moving from prototype to production. Hallucination in agentic AI systems that query real data is qualitatively different from hallucination in general-purpose LLMs, and it is more dangerous because the outputs look authoritative.

There are three distinct hallucination risk zones in a lakehouse AI agent:

  • SQL generation: The model generates SQL that is syntactically valid but semantically wrong. For example, when asked “What is our revenue growth this quarter?”, the model might generate a query that compares the wrong date ranges, uses the wrong aggregation function, or joins tables on incorrect keys, and then returns a confident, formatted answer with the wrong numbers.
  • Cross-source synthesis: When the agent queries multiple federated sources and synthesizes results, the risk compounds. The model may correctly retrieve customer counts from Amazon S3 and revenue figures from Snowflake, but incorrectly draw conclusions that aren’t supported by either dataset individually.
  • Memory-augmented reasoning: When long-term memory is active, the model may blend historical context with current query results in ways that are factually incorrect. For example, it might apply a business rule that was true six months ago but has since changed.

To improve, before any agent output informs a business decision, apply the following three-step validation framework:

  • Step 1: Source verification. Can you trace the answer back to a specific table, column, and row count? If the agent can’t show you the SQL and the row count, the answer is unverified.
  • Step 2: Reasonableness check. Does the answer fall within expected ranges? A sudden 10x spike in customer count is a signal to investigate.
  • Step 3: Cross-validation. For critical decisions, run the equivalent query directly in Athena or your BI tool and compare. Discrepancies reveal either a model reasoning error or a data quality issue. Resolve both before the answer is trusted.

These lessons don’t diminish the value of the architecture. They make it production-ready. The teams that move fastest with agentic AI are not the ones who skip these guardrails. They’re the ones who build them in from the start and spend less time firefighting in production.

Alternative to the unified catalog approach

In case you face technical and process challenges to unify catalogs across providers, you can let each data producer expose the metadata and data through MCP servers, as represented in the following diagram. In this approach, each producer takes the responsibility of maintaining the MCP servers and exposing them to the context layer. While this approach provides autonomy to data owners to operate independently and with flexibility, it also creates operational overhead to synchronize all metadata in a consistent way.

Alternative architecture where each data producer exposes its metadata and data through its own MCP server to the context layer

What’s next

In Part 2 of this series, we walk through the full implementation step by step, including hands-on scripts to:

  • Load example sales datasets into Databricks and marketing data to Snowflake as Iceberg tables, and federate them into AWS Glue Data Catalog through the Iceberg REST API.
  • Register Google BigQuery as a native federated data source in Amazon SageMaker, instead of a traditional AWS Lambda connector integration.
  • Create a customer master table as a native Iceberg table in Amazon S3.
  • Run a single SQL query in Amazon Athena that joins all four sources across two federation patterns, with no data movement.
  • Deploy an AI agent on Amazon Bedrock AgentCore that can autonomously query the same unified catalog using Amazon Athena and answer complex business questions in natural language queries. In addition, integrate AgentCore Memory to persist user context.

Conclusion

In this post, we summarized how you can unify data access across multiple cloud and ISV providers on AWS with the combination of catalog federation, query federation, and data movement to AWS. We then explained how AWS Glue Data Catalog and Lake Formation help provide unified catalog and access governance, and how AI agents hosted in Amazon Bedrock AgentCore can access it using MCP servers to explore the metadata context, convert user natural language queries to SQL, and use Amazon Athena to run the query across data sources to get the response to the end user. In addition, we provided an overview of different data ingestion methods to build a lakehouse architecture on AWS, including AWS Interconnect – multicloud and where it adds value.

We also provided architecture trade-offs and best practices to integrate the service capabilities. In the next post (Part 2), we will take a specific use case and provide a step-by-step implementation guide to unify the catalog and deploy the agent to Amazon Bedrock AgentCore.


About the author

Sakti Mishra

Sakti Mishra

Sakti is a Principal Data and AI Solutions Architect at AWS, where he helps customers modernize their data architecture and define end-to-end data strategies, including data security, accessibility, governance, and more. He is also the author of Simplify Big Data Analytics with Amazon EMR and AWS Certified Data Engineer Study Guide. Outside of work, Sakti enjoys learning new technologies, watching movies, and visiting places with family. You can connect with Sakti through his LinkedIn profile.

Build an autonomous ecommerce assistant with AWS End User Messaging, Amazon Bedrock AgentCore, and OpenClaw

Post Syndicated from Rommel Sunga original https://aws.amazon.com/blogs/messaging-and-targeting/build-an-autonomous-ecommerce-assistant-with-aws-end-user-messaging-amazon-bedrock-agentcore-and-openclaw/

In this post, we walk through Claw Boutique, an open-source reference architecture that connects a web storefront, WhatsApp, email, and Telegram into a single OpenClaw-driven ecommerce experience on AWS. Buyers interact through WhatsApp and a web store. The shop owner manages everything from Telegram, where an artificial intelligence (AI) agent processes restock, refund, and order commands.

The project uses Amazon Bedrock AgentCore Runtime with the Strands Agents SDK, an open-source framework for building AI agents, for real-time buyer chat. Amazon Elastic Kubernetes Service (Amazon EKS) hosts the seller-side AI agent (OpenClaw, an open-source AI agent gateway). AWS End User Messaging Social provides managed WhatsApp Business integration. The entire stack deploys with a single AWS Cloud Development Kit (AWS CDK) command.

Architecture overview

The architecture separates concerns into three channels that share a common Store API and database.

Claw Boutique architecture on AWS showing the buyer, seller, and web storefront channels

Figure 1 – Claw Boutique architecture on AWS

Buyer channel (WhatsApp): Inbound WhatsApp messages arrive through AWS End User Messaging Social, which provides a managed WhatsApp Business API integration. Messages publish to an Amazon Simple Notification Service (Amazon SNS) topic, which triggers a Dispatcher AWS Lambda function. The dispatcher invokes a Strands Agent hosted on Amazon Bedrock AgentCore Runtime, running Amazon Nova Lite for real-time, tool-calling conversations. AgentCore Memory provides session continuity across messages. The agent can look up products, check order status, escalate issues, and send replies back through WhatsApp.

Seller channel (Telegram): The store owner receives stock alerts, review escalations, and order notifications on Telegram. An AI agent runs on Amazon EKS via the OpenClaw gateway. The owner replies with natural language commands such as “restock hoodies” or “apologize to the buyer,” and the agent runs the appropriate Store API calls.

Web storefront: Amazon CloudFront serves a static site from Amazon Simple Storage Service (Amazon S3). The checkout flow calls the Store API through Amazon API Gateway. The same API backs both the storefront and the admin dashboard.

All three channels converge on a single Store API Lambda function (Python/Flask) backed by Amazon Relational Database Service (Amazon RDS) for MySQL. Amazon Simple Email Service (Amazon SES) sends transactional email messages for order confirmations, shipping updates, and refund notices.

How it works: The order lifecycle

A single order touches the web storefront, WhatsApp, email, Telegram, and the admin dashboard. Here is the full flow.

1. Place an order

You visit the storefront, add items to the cart, and check out. The Store API creates the order in Amazon RDS and returns an order number.

The Claw Boutique web storefront with product listings

Figure 2 – The Claw Boutique storefront

2. Order confirmation on WhatsApp and email

Two things happen right after checkout. The buyer receives a WhatsApp message with the order number, items, and total, followed by a feedback survey asking them to rate their experience from 1 to 5. At the same time, Amazon SES sends a confirmation email with the same order details.

WhatsApp order confirmation message followed by a feedback survey rating prompt

Figure 3 – WhatsApp order confirmation and feedback survey

Order confirmation email sent through Amazon SES

Figure 4 – Order confirmation email via Amazon SES

3. Stock alert on Telegram

Every purchase triggers a stock check. If any item is out of stock, running low (fewer than 5 units), or projected to sell out within 7 days, the seller gets a Telegram alert with current stock levels and sell-through rates. The seller can reply with a command such as “restock hoodies 20” and the AI agent runs it.

Telegram stock alert showing stock levels with a restock command reply

Figure 5 – Telegram stock alert with restock command

4. Negative feedback triggers an escalation

The buyer replies “1” to the WhatsApp survey. The Store API creates an escalation record and sends the seller a Telegram alert with the buyer’s name, phone number, rating, and review text.

Telegram review escalation alert with buyer details and rating

Figure 6 – Telegram review escalation alert

5. Seller resolves the issue from Telegram

The seller replies “apologize” on Telegram. The AI agent looks up the unresolved escalation and takes four actions: sends a WhatsApp apology to the buyer, sends a refund confirmation email via Amazon SES, marks the order as “refunded” in the database, and resolves the escalation. If there are multiple open escalations, the agent lists them and asks which one to resolve.

6. Admin dashboard

The seller can also open the admin dashboard to view orders (now showing “refunded” status), escalation history, stock levels, and AI-generated business insights based on order patterns and buyer feedback.

Admin dashboard showing orders, escalation history, stock levels, and business insights

Figure 7 – Admin dashboard with orders and insights

Ordering directly through WhatsApp

Buyers can also browse and order by texting the WhatsApp business number directly. The Strands Agent on AgentCore manages the full conversation: showing available products, checking order status, answering product questions, and escalating issues to the store owner.

Ordering through WhatsApp using Amazon Bedrock AgentCore

Figure 8 – Ordering through WhatsApp via Amazon Bedrock AgentCore

Why two AI models?

Claw Boutique uses two AI models for different purposes, each chosen for the characteristics that matter most in its channel.

Amazon Nova Lite (via Amazon Bedrock AgentCore) for the buyer channel: Buyer-facing WhatsApp interactions need to be fast and cost-effective. Amazon Nova Lite provides sub-second responses with reliable tool calling at a fraction of the cost of larger models. AgentCore Runtime hosts the agent container, while AgentCore Memory manages conversation history per buyer phone number. The Strands Agents SDK handles tool definitions, orchestration, and model interaction with minimal boilerplate.

AI agent (via OpenClaw on Amazon EKS) for the seller channel: The seller channel involves more complex tasks: interpreting ambiguous commands, managing multi-step workflows (such as resolving escalations that span WhatsApp, email, and the database), and generating business insights. The model’s reasoning capabilities are well suited for these. OpenClaw provides the gateway, tool execution, and memory management layer.

This approach keeps buyer-facing latency low and costs predictable, while giving the seller access to deeper reasoning when managing the business.

Prerequisites

Before you deploy, make sure you have the following:

  • AWS Command Line Interface (AWS CLI) configured with credentials.
  • Node.js 18+ and Docker running locally.
  • A Telegram bot token (obtainable from @BotFather).
  • A WhatsApp Business Account linked to AWS End User Messaging Social.
  • A verified Amazon SES email address.

Deploying the solution

The entire stack deploys with AWS CDK. A single cdk deploy command provisions the Amazon Virtual Private Cloud (Amazon VPC), Amazon EKS cluster, Amazon RDS database, Lambda functions, Amazon API Gateway, Amazon CloudFront distribution, Amazon S3 bucket, Amazon SNS topic, and all AWS Identity and Access Management (IAM) roles and security groups. AWS CDK also runs database initialization (schema and seed data), Docker image build, Amazon Elastic Container Registry (Amazon ECR) push, and Amazon EKS deployment.

Configuration values (Telegram token, WhatsApp IDs, Amazon SES email) go into a CDK context file. Cold deploy takes about 25-30 minutes.

You can find the full source code and deployment instructions in the GitHub repository.

Cleaning up

To avoid ongoing charges, delete the resources created in this walkthrough when you’re done experimenting. Run the following command from the cdk/ directory:

cd cdk && npx cdk destroy

This removes the Amazon EKS cluster, Amazon RDS database, Lambda functions, and all other resources created by the stack. No context values are needed for destroy.

Conclusion

In this post, we showed how to build an ecommerce bot using OpenClaw and Amazon Bedrock AgentCore. By combining AWS End User Messaging Social for WhatsApp, Amazon Bedrock AgentCore Runtime for real-time buyer conversations, and Amazon EKS for a seller-side AI agent, you can create a system where buyers order through the channels they already use, and store owners manage their business from a single Telegram chat.

The project is open source and deploys with a single AWS CDK command. You can use it as a starting point and adapt it to your own product catalog, messaging channels, and business logic.

To learn more and get started:


About the authors

Top announcements of the AWS Summit in New York, 2026

Post Syndicated from AWS News Blog Team original https://aws.amazon.com/blogs/aws/top-announcements-of-the-aws-summit-in-new-york-2026/

Today at the AWS Summit in New York City, Swami Sivasubramanian, AWS VP of Agentic AI, provided the day’s keynote. Here’s our roundup of the biggest announcements from the event:

New in Amazon Bedrock AgentCore
We’re introducing new capabilities on Amazon Bedrock AgentCore: connecting AI agents to organizational, web, and paid knowledge, helping teams find and fix what’s going wrong in production, and enforcing controls that scale as agents grow more capable.

Together, these capabilities help you build more capable agents faster, govern those agents with controls that scale, and improve them continuously. To learn more, read our blog post covering all the new features.

New in AI-based security tools

New in building AI-based applications 

  • Introducing Kiro for iOS — Kiro introduces a native iOS app, available in a gated preview, built for real engineering work that gives developers a new surface to kick off, monitor, steer, and interact with their Kiro sessions directly from their phone. That means you can now start sessions, check back when they’re done, review diffs, and approve changes all while staying connected to your work with no laptop running.
  • AWS DevOps Agent adds release management capabilities to assess code changes before production — You can use a new release readiness review of code changes and autonomous release testing. These new features verify every change against the natural language standards you give to the DevOps Agent and run change-specific tests in production-like environments.
  • Proactively reduce tech debt autonomously with AWS Transform – continuous modernization — You can use continuous analysis (preview) to automatically scan your code repositories against configurable baselines and generates findings in hours, not weeks. Once you’ve identified and prioritized findings, you can configure autonomous remediations that generate pull requests for affected repositories automatically.

In addition to the keynote announcements, we have other important launches this week:

Introducing Amazon Bedrock Managed Knowledge Base for faster, more accurate enterprise AI applications

Post Syndicated from Daniel Abib original https://aws.amazon.com/blogs/aws/introducing-amazon-bedrock-managed-knowledge-base-for-faster-more-accurate-enterprise-ai-applications/

Today, we’re announcing Amazon Bedrock Managed Knowledge Base, a new set of capabilities that enables developers to build enterprise-grade generative AI applications with their proprietary data in minutes. Organizations building agentic AI applications need secure, reliable, and up-to-date access to enterprise-wide data to deliver accurate, fast, and trusted outcomes. Managed Knowledge Base abstracts away the complexity of building and managing retrieval-augmented generation (RAG) pipelines, allowing developers to focus on business outcomes rather than infrastructure management.

Developers building knowledge bases for their agents face three key challenges today:

  • Connecting to enterprise data – Enterprise knowledge lives across disparate systems with different content types, access control lists, and document formats. Building and maintaining custom connectors for each source adds complexity that slows down development.
  • Optimizing RAG accuracy – Best practices for retrieval-augmented generation keep evolving. Developers need to experiment with different parsing strategies, chunking approaches, embedding models, and agentic retrieval behaviors to get accurate answers from their data.
  • Managing infrastructure at scale – Organizations need to serve large knowledge bases with millions of documents, or manage thousands of smaller knowledge bases across teams. Both patterns require reliable infrastructure, security enforcement, and cost control.

These challenges require developers to repeatedly perform undifferentiated work instead of focusing on their applications.

Amazon Bedrock Managed Knowledge Base addresses these challenges by abstracting away the multiple infrastructure components developers traditionally have to assemble and maintain themselves (storage, retrieval, embeddings, re-ranking, and foundation model selection) into a single managed primitive. By default, the service automatically selects and manages a default embeddings model, re-ranker model, and foundational model on your behalf, so you can get up to speed quickly without needing to pick or maintain one yourself. On top of this managed foundation, three core innovations further improve ease of use and accuracy:

  • Native data connectors – Six pre-built ingestion connectors that natively pull enterprise data and permissions from SaaS applications, eliminating the overhead developers face in managing application-specific requirements. At launch, we support Amazon S3, SharePoint, Confluence, Web Crawler, Google Drive, and OneDrive.
  • Smart Parsing – Different content types and sources require different approaches to achieve accurate retrieval. Smart Parsing handles this complexity automatically, selecting the right parsing strategy for each data type and connector to provide the highest accuracy for your agents.
  • Agentic Retriever – Optimized for complex queries that require multiturn, multihop retrieval within a single knowledge base or across multiple knowledge bases. Agentic Retriever automatically infers end-user intent and draws relevant context from institutional knowledge spread across data sources and modalities.

With just a few lines of code, Amazon Bedrock Managed Knowledge Base automatically manages and scales the end-to-end RAG pipeline that powers your enterprise knowledge agents. For agent builders, it’s available as a pre-built target type in Amazon Bedrock AgentCore Gateway, reducing integration to a few lines of code, auto-generating role-based permissions, and providing observability and evaluation metrics in the AgentCore Observability dashboard.

Getting started with Amazon Bedrock Managed Knowledge Base
Creating a Managed Knowledge Base is straightforward. Navigate to the Amazon Bedrock AgentCore console or the Amazon Bedrock console, open the Knowledge Bases page, and choose Create Managed KB. The experience is the same in both consoles. You will see that Unstructured Vector Store KB is now available as the recommended option, alongside the other knowledge base types you may already be familiar with:

Picture 1 – Knowledge Bases list page in the Amazon Bedrock AgentCore console showing the Type column with different KB types and the Create Managed KB button

When creating a new Knowledge Bases, you can connect to your enterprise data sources by choosing from the list of supported connectors directly from a dropdown. AWS Identity and Access Management (IAM) roles are automatically created, and you can choose to edit these permissions if needed:

Picture 2 – Create Knowledge Base page showing the Data source dropdown expanded with all supported connectors: Amazon S3, Confluence, Custom, Google Drive, One Drive, SharePoint, and Web Crawler

An optimized set of defaults will be presented, allowing you to create your knowledge base in just a few clicks. Once the data is synced, you can integrate the knowledge base with your agent or provide it as a tool for your foundation model and start querying.

Smart Parsing for accurate data ingestion
One of the key challenges in building knowledge bases is preparing diverse data types for accurate retrieval. Once you point Managed Knowledge Base at your data sources, Smart Parsing automatically determines the optimal parsing strategy for each data type and connector, no extra configuration is required.

Smart Parsing combines multiple techniques:

  • Connector-specific data models – Optimized handling for each data source. For example, the Web Crawler connector preserves HTML structure including embedded images and tables, ensuring rich content is not dropped during ingestion. SharePoint connectors maintain document hierarchy and relationships between files.
  • Multimodal processing – Automatic detection and processing of different content types within documents. The system identifies bounding boxes in documents, then sends them to foundation models for data extraction, captioning, and scene description in video files.
  • Optimized chunking – Smart Parsing leverages foundation models to understand document structure and extract meaningful content, ensuring that complex documents with mixed formats are properly indexed. Intelligent defaults balance retrieval accuracy with performance based on document type and content structure, while advanced users can customize chunking strategies when needed.

This automated approach eliminates weeks of experimentation typically required to achieve production-quality retrieval accuracy, while still preserving the flexibility to customize when needed.

Using Agentic Retriever for complex queries
After your data is ingested, you can start querying your knowledge base. Generative AI applications often struggle with complex user queries that require reasoning, recursive multi-step retrieval, and intermediate evaluations of results. Consider a user asking two related questions: “What is the cloud infrastructure budget for the ML platform team?” and “Does our expense policy allow prepaying annual commitments?” A single retrieval step might surface documents about the ML platform team but fail to connect the budget information with the expense policy needed to fully answer the question.

Picture 3 – Agentic Retriever decomposes complex user queries into a step-by-step plan, performing multi-hop retrieval across multiple knowledge bases and combining results to deliver accurate, grounded responses

Agentic Retriever solves this by creating a step-by-step query plan: 1. Which team owns the ML platform, and what is their cloud infrastructure budget? 2. What does the expense policy say about prepaying annual commitments? 3. Does the policy allow the ML platform team to prepay against this budget?

The system performs multi-hop retrieval and reasoning at each step, and once it has gathered sufficient relevant passages, it stops the search process and returns the top results. By abstracting away the complexity of building a separate multi-hop reasoning pipeline, this approach dramatically improves accuracy for complex queries while letting developers focus on their agentic search applications instead of orchestration logic.

You can try Agentic Retriever directly from the test panel of your knowledge base in the Amazon Bedrock AgentCore console. Select Agentic retrieval only as the retrieval type to let the system automatically plan and execute multi-step queries across your knowledge bases:

Picture 4 – Test Knowledge Base panel showing Agentic retrieval with answer generation selected as the retrieval type, with model selection and maximum agentic iterations options

Enabling MCP with Bedrock AgentCore
Amazon Bedrock Managed Knowledge Base seamlessly integrates with AgentCore Gateway as a native target type. This integration eliminates the need for manual integration and provides built-in observability, policy enforcement, and automatic permission management.

You can navigate to the Amazon Bedrock AgentCore console or SDK and create an AgentCore Gateway or select an existing one. When adding targets to your gateway, you will find Knowledge Base as a new pre-built target type alongside other options such as MCP server, Lambda ARN, REST API, and other integrations. Simply select your knowledge base ID to expose it through the gateway:

Picture 5 – Add targets page in AgentCore Gateway showing Knowledge Base as a new pre-built target type, with the knowledge base ID selector and runtime retrieval mode options

Add targets page in AgentCore Gateway showing Knowledge Base as a new pre-built target type, with the knowledge base ID selector and runtime retrieval mode options

Gateway exposes the standard Model Context Protocol (MCP), so the knowledge base tools are automatically discovered by clients from any MCP-compatible framework, including Strands Agents, LangChain, CrewAI, LlamaIndex, and LangGraph. No custom integration code is required.

Model choice and flexibility
Amazon Bedrock Managed Knowledge Base preserves the flexibility developers expect from Amazon Bedrock. Every foundation model available on Bedrock can power the generation step, and developers can select from different embedding and re-ranking models to optimize retrieval for their specific use case, enabling teams to fine-tune accuracy and cost-performance without changing infrastructure.

Unlike managed solutions that lock you into specific model providers, Amazon Bedrock Managed Knowledge Base separates the infrastructure management (connectors, parsing, storage, retrieval orchestration) from model selection. This means you can:

  • Take advantage of the latest models – Adopt the latest embedding, re-ranking, and foundation models as they become available to improve accuracy, latency, and cost for your application without rebuilding your RAG pipeline.
  • Optimize for price-performance – Choose smaller, faster models for simple queries and more capable models for complex reasoning tasks, all using the same knowledge base infrastructure.
  • Use Bedrock embedding models – While Smart Parsing provides optimized defaults, you can configure Bedrock embedding models when your domain requires specialized semantic understanding.
  • Maintain consistency with existing applications – If you’re already using Bedrock Knowledge Bases APIs (Retrieve, StartIngest, StopIngest, IngestKnowledgeBaseDocuments), Managed Knowledge Base uses the same APIs, so migration requires no code changes, just point to the new knowledge base ID.

This approach ensures you can spend time on your generative AI application without losing the ability to change models based on evolving requirements or new model capabilities.

Get started today
Amazon Bedrock Managed Knowledge Base is available today in the US East (N. Virginia), US West (Oregon), Asia Pacific (Sydney, Tokyo), Europe (Dublin, Frankfurt, London), and AWS GovCloud (US-West) Regions. For Regional availability and future roadmap, visit AWS Capabilities by Region.

With Bedrock Managed Knowledge Base, you pay for what you use with no upfront commitments. Pricing is based on two dimensions: the size of indexed data stored and the number of retrievals performed (on-demand). For detailed pricing information, visit the Amazon Bedrock pricing page. Bedrock is also a part of the AWS Free Tier that new AWS customers can use to get started at no cost and explore key AWS services.

These capabilities work with any open source framework such as CrewAI, LangGraph, LlamaIndex, and Strands Agents, and with any foundation model. Bedrock services can be used together or independently, and you can get started using your favorite AI-assisted development environment with the AgentCore open source MCP server.

To learn more and get started quickly, visit the Bedrock Knowledge Bases Developer Guide.

Daniel Abib

Announcing Web Search on Amazon Bedrock AgentCore: Ground your AI agents in current, accurate web knowledge

Post Syndicated from Channy Yun (윤석찬) original https://aws.amazon.com/blogs/aws/announcing-web-search-on-amazon-bedrock-agentcore-ground-your-ai-agents-in-current-accurate-web-knowledge/

Today, we’re announcing the general availability of Web Search on Amazon Bedrock AgentCore, a fully managed tool that enables agents to ground responses in current, cited web knowledge with zero data egress from customer’s secured AWS environment.

Web Search uses a built-in connector target on Bedrock AgentCore Gateway using the Model Context Protocol (MCP). Your agent sends a natural-language query, and Web Search returns most relevant snippets, source URLs, titles, and publication dates that the model can reason over to produce a grounded response.

It is built on Amazon’s search infrastructure, informed by years of experience powering agentic search experiences across Alexa+, Amazon Quick, and Kiro. It uses a multi-source grounding approach that combines Amazon’s web index with structured knowledge graph data. Beyond standard web results, this gives agents access to Amazon Knowledge Graph with verified facts, helping them retrieve more relevant and accurate responses than traditional web search alone.

With this launch, you can focus on building agents instead of manually adding web search to agents on Bedrock AgentCore and managing its infrastructure. Your AI agent looks at user question, retrieves the latest facts, and then takes any necessary action grounded in current developments beyond a model’s training data. You can also meet enterprise governance policies without sending user prompts and retrieval queries to external search API providers outside of AWS.

Web Search on Bedrock AgentCore in action
To get started, create the Bedrock AgentCore Gateway with Web Search tool target in the Bedrock AgentCore console. When the Gateway URL is created, you can interact with API call, Command Line Interface (CLI), or MCP Inspector.

To add Web Search tool target when creating the Gateway, choose MCP target as a target protocol and Connectors as a target type. You can select the Web Search tool as a preconfigured target to retrieve most relevant web search results including links, snippets, and metadata.

After creating your gateway, you can find the Web Search tool target on the detail page of your gateway. You can also add a new Web Search tool target to an existing gateway.

To interact with Web Search tool, use the sample invocation code in the View invocation code section. You can use code snippets through Python codes with API requests, MCP Python SDK, Strands MCP Client, and MCP Inspector.

For example, you can interact with the MCP Inspector, an interactive developer tool for testing and debugging MCP servers. When you connect to the MCP server through the Gateway resource URL, you will find a Web Search tool for each connector target on the Gateway. Enter input the web search query and choose Run Tool to get the results.

To learn more about how to use Web Search on Bedrock AgentCore, visit the Bedrock AgentCore Gateway documentation.

Customer voices
Some of our customers had early access to this new feature. This is what they shared with us:

Benchling helps scientists accelerate R&D, making it easy to centralize scientific data, collaborate across teams, and access insights. Nicholas Larus-Stone, Head of AI Agents at Benchling shared “Scientists using Benchling AI can now ask about a target they’re actively working on and get answers grounded in both their institutional data in Benchling and published literature. The result is more complete science, and hypothesis generation done right. Because we’re using the Web Search tool on Amazon Bedrock AgentCore, customers have a secure, governed environment to bring that high quality published data into their workflows without compromising how they manage their data.”

Gen Digital leads consumer and small business cyber safety, offering antivirus, antimalware, identity and privacy protection, virtual private networks, and cloud backup. Iskander Sanchez-Rola, Senior Director of AI & Innovation, Gen Digital shared “With the Web Search tool on Amazon Bedrock AgentCore, Norton Revamp helps professionals build their online reputation with current, grounded content ideas shaped by what’s actually happening in the world today. What we value most is that AWS uses its own search index and keep queries within our trusted AWS environment.”

To read more customer stories, visit the Amazon Bedrock Customers.

Now available
Web Search on Amazon Bedrock AgentCore is generally available today in the US East (N. Virginia) Region. For Regional availability and a future roadmap, visit the AWS Capabilities by Region.

You can get started with Web Search on Bedrock AgentCore at no additional cost. You pay only for the data transfer charges you use for the Gateway. New AWS customers also receive up to $200 in Free Tier credits. To learn more, visit the Amazon Bedrock AgentCore pricing page.

Try it in the Amazon Bedrock AgentCore console and send feedback to AWS re:Post for Amazon Bedrock AgentCore or through your usual AWS Support contacts.

— Channy

Building AI shopping agent using Amazon Bedrock AgentCore Runtime and Amazon OpenSearch Service

Post Syndicated from Omama Khurshid original https://aws.amazon.com/blogs/big-data/building-ai-shopping-agent-using-amazon-bedrock-agentcore-runtime-and-amazon-opensearch-service/

In this post, we explore how to build an online shopping AI agent. We focus on its architecture and implementation with Amazon OpenSearch Service, Amazon Bedrock AgentCore, and Strands Agents. Amazon Bedrock AgentCore is an agentic platform for deploying and operating those agents and tools securely at scale without managing infrastructure. AgentCore Runtime is the secure, serverless runtime that hosts your Strands Agents and tools as containerized applications. Strands Agents is an open source SDK for building AI agents. In this SDK, an agent is defined by a model, tools, and a prompt. Tools are callable functions that allow agents to perform actions beyond text generation, such as API calls, database queries, and file operations. The framework lets the model autonomously plan steps and invoke tools to complete tasks.

Today’s AI shopping assistants understand natural language, context, and shopping intent, creating a more human-like interaction. These assistants handle complex shopping requirements, such as “Find me a formal dress under $200 that’s appropriate for a summer wedding.” They maintain conversation history, process follow-up questions naturally, and provide personalized recommendations based on user preferences and past interactions. Customers can use visual search to upload images of items that they want, and the AI finds similar products across multiple retailers, matching styles and patterns. The goal is to provide instant, relevant, and personalized assistance at scale, creating a more efficient shopping journey for consumers worldwide.

AI agents combined with Retrieval Augmented Generation (RAG) on Amazon OpenSearch Service represent an evolution in conversational search. This integration builds AI agents on enriched catalogs, supporting context-aware and autonomous search experiences while maintaining accuracy and relevance through grounded responses.

Solution overview

The following diagram illustrates the solution architecture of an AI-powered online shopping agent built using Strands Agents, Amazon Bedrock AgentCore Runtime, and Amazon OpenSearch Service. For simplicity, the diagram doesn’t show authentication and authorization. In a production setup, secure access to the backend by using mechanisms such as Amazon API Gateway, AWS Identity and Access Management (IAM) roles, or OAuth-based authentication.

Architecture diagram showing an AI shopping agent: a user prompt flows from the front end to AgentCore Runtime, which routes the request to a Strands Retail Agent that calls a search tool against Amazon OpenSearch Service and an Amazon Bedrock LLM, then returns a natural-language response to the user.

The following is a walkthrough of the reference architecture:

  1. The user submits a question through the front-end application. AgentCore Runtime receives the request and routes it to the Strands Retail Agent.
  2. The Strands Agent processes the task and invokes the search_product_catalog tool.
  3. OpenSearch Service performs semantic search and returns relevant product results.
  4. The Strands Agent invokes Amazon Bedrock large language models (LLMs) to generate a natural language response.
  5. The agent response is returned to the user through the front end.

Walkthrough

The following section walks you through how to build an online shopping AI agent.

Prerequisites

To implement this solution, you need an AWS account. You also need an OpenSearch Service domain with OpenSearch version 2.13 or later. You can use an existing domain or create a new domain.

To use the vector search capabilities of OpenSearch Service with Strands Agents on AgentCore, you use ingest pipelines. These ingestion pipelines apply built-in processors to pre-process your documents before you index them in OpenSearch Service.

You use the text_embedding processor, which relies on the ML Commons plugin and a registered embedding model—Amazon Nova Multimodal Embeddings on Amazon Bedrock. OpenSearch Service uses the ML Commons plugin to generate vector embedding for your data and uses the same model to convert incoming queries into vectors. This supports semantic search across your indexed content.

You extend your semantic search backend by adding an agent built with Strands Agents and deployed on Amazon Bedrock AgentCore.

Code samples provided in this post are tested in Python 3.11. You only need to install Python 3.11 in your environment to execute the python scripts. You also need Node.js 18 or later installed to use the AgentCore CLI. The provided code scripts will deploy into your AWS account so make sure your terminal has access to necessary AWS credentials.

Install AgentCore CLI

Install the AgentCore CLI globally using npm:

npm install -g @aws/agentcore

Python Dependencies

You also need to create a requirements.txt file with following dependencies in your workspace to deploy the agents.

boto3
uv
opensearch-py
requests-aws4auth
strands-agents
strands-agents-tools
bedrock-agentcore

Run pip install -r requirements.txt in your terminal to install the required dependencies. To avoid conflicts with other dependencies in your system, you can use a virtual environment.

Now, walk through each step.

Step 1: Configure IAM permissions

Complete the following steps to register the Nova Multimodal Embeddings model with OpenSearch Service and verify that your OpenSearch Service domain has permission to invoke the Amazon Bedrock API.

  1. Go to the IAM console and create a new role with a custom trust policy. Add the following trust policy.
    {
      "Version": "2012-10-17",
      "Statement": [
        {
          "Sid": "Statement1",
          "Effect": "Allow",
          "Principal": {
            "Service": "opensearchservice.amazonaws.com"
          },
          "Action": "sts:AssumeRole"
        }
      ]
    }

  2. Skip adding a permission policy.
  3. Give your role a name and create it. For this post, we use OpenSearchBedrockEmbeddingRole as the role name. OpenSearch Service uses this role to invoke the Nova Multimodal Embeddings model on Amazon Bedrock.
  4. On the Permissions tab, attach an inline policy with the following permissions. For this post, we name this policy OpenSearchBedrockEmbeddingPolicy.
    {
      "Version": "2012-10-17",
      "Statement": [
        {
          "Sid": "Statement1",
          "Effect": "Allow",
          "Action": [
            "bedrock:InvokeAgent",
            "bedrock:InvokeModel"
          ],
          "Resource": [
            "arn:aws:bedrock:us-east-1::foundation-model/*"
          ]
        }
      ]
    }

  5. Create a passRole policy with the following JSON document and assign it to the IAM role that creates the ML connector. This lets the principal running the Python code pass the OpenSearchBedrockEmbeddingRole to OpenSearch. Replace <your-aws-account-id> with your own AWS account ID.
    {
      "Version": "2012-10-17",
      "Statement": [
        {
          "Effect": "Allow",
          "Action": "iam:PassRole",
          "Resource": "arn:aws:iam::\$<your-aws-account-id>:role/OpenSearchBedrockEmbeddingRole"
        }
      ]
    }

  6. By using fine-grained access control (FGAC), map the IAM role as a backend role for the ml_full_access role in the OpenSearch Dashboards Security plugin. This mapping lets the user create ML connectors:
    1. Log in to OpenSearch Dashboards and open the Security page from the navigation menu.
    2. Choose Roles and select ml_full_access.
    3. Choose Mapped Users and Manage Mapping.
    4. Under Backend roles, add the ARN of the IAM role that you created in the previous steps.

Animated demo of OpenSearch Dashboards Security plugin showing the ml_full_access role with the Mapped Users tab open and an IAM role being added as a backend role.

Step 2: Connect to the model by using OpenSearch ML Connectors

In this section, you create an ML connector to link OpenSearch Service with the Bedrock Nova Multimodal Embeddings model. You then register and deploy the model so you can use it for neural search queries.

  1. Create a file named create-connector.py with the following code. Replace <your hostname>, <your region>, and <your account id> placeholders within the code.
import boto3
import requests
from requests_aws4auth import AWS4Auth
host = '<your hostname>'##CHANGE THIS
region = '<your region>' ##CHANGE THIS
account_id = '<your account id>' ##CHANGE THIS
service = 'es'
credentials = boto3.Session().get_credentials()
awsauth = AWS4Auth(credentials.access_key, credentials.secret_key, region, service, session_token=credentials.token)
path = '/_plugins/_ml/connectors/_create'
url = host + path
payload = {
"name": "Amazon Bedrock Nova multimodal model - text embedding",
"description": "Test connector for Amazon Bedrock Nova multimodal model - text embedding",
"version": 1,
"protocol": "aws_sigv4",
"credential": {
"roleArn": f"arn:aws:iam::{account_id}:role/OpenSearchBedrockEmbeddingRole"
},
"parameters": {
"region": region,
"service_name": "bedrock",
"model": "amazon.nova-2-multimodal-embeddings-v1:0",
"input_docs_processed_step_size": 1,
"dimensions": 1024,
"embeddingTypes": [
"float"
],
"truncationMode": "NONE"
},
"actions": [
{
"action_type": "predict",
"method": "POST",
"headers": {
"content-type": "application/json",
"x-amz-content-sha256": "required"
},
"url": "https://bedrock-runtime.${parameters.region}.amazonaws.com/model/${parameters.model}/invoke",
"request_body": "{\\n \\"taskType\\": \\"SINGLE_EMBEDDING\\",\\n \\"singleEmbeddingParams\\": {\\n \\"embeddingPurpose\\": \\"GENERIC_INDEX\\",\\n \\"embeddingDimension\\": ${parameters.dimensions},\\n \\"text\\": {\\n \\"truncationMode\\": \\"${parameters.truncationMode}\\",\\n \\"value\\": \\"${parameters.inputText}\\"\\n }\\n }\\n}",
"pre_process_function": "connector.pre_process.bedrock.nova.text_embedding",
"post_process_function": "connector.post_process.bedrock.nova.embedding"
}
]
}
headers = {"Content-Type": "application/json"}
r = requests.post(url, auth=awsauth, json=payload, headers=headers, timeout=15)
print(r.status_code)
print(r.text)
  1. Run python create-connector.py in your terminal by using the IAM role with ml_full_access and passRole permissions created in the previous step. This script creates a connector between OpenSearch Service and the Bedrock Nova Multimodal Embeddings model.
  2. The program responds with connector_id. Take a note of it. Then, navigate to OpenSearch Dashboards and open Dev Tools. Create a model group against which to register this model in the OpenSearch Service domain.
POST /_plugins/_ml/model_groups/_register
{
  "name": "agent-conversational-search-model-group",
  "description": "A model group for bedrock Nova embedding models used for conversational search"
}
  1. Register a model by using connector_id and model_group_id.
POST /_plugins/_ml/models/_register
{
  "name": "nova-2-multimodal-embedding-v1",
  "function_name": "remote",
  "model_group_id": "<model group id>",
  "description": "Nova 2 Multimodal Embeddings Model",
  "connector_id": "<connector id>",
  "interface": {}
}
  1. Run the following API call to deploy the model. Use the registered model ID from the previous step.
POST /_plugins/_ml/models/<registered-model-id>/_deploy

Step 3: Create an ingest pipeline for data indexing

Use the following code to create an ingest pipeline for data indexing. The pipeline establishes a connection to the embedding model, retrieves the embedding for the title field, and stores it in the OpenSearch index.

PUT /_ingest/pipeline/nova_multimodal_embedding
{
  "description": "Text embedding pipeline using nova_multimodal_embedding",
  "processors": [
    {
      "text_embedding": {
        "model_id": "<deployed model id>",
        "field_map": {
          "title": "title_vector"
        }
      }
    }
  ]
}

Step 4: Create an index for storing data

Create an index named product for storing data by using Dev Tools. This index stores raw text and 1024-dimensional embeddings of the title field, and uses the ingest pipeline you created in the previous step.

PUT /product
{
  "settings": {
    "index": {
      "default_pipeline": "nova_multimodal_embedding",
      "knn": true
    }
  },
  "mappings": {
    "properties": {
      "title": {
        "type": "text",
        "analyzer": "standard"
      },
      "title_vector": {
        "type": "knn_vector",
        "dimension": 1024,
        "method": {
          "name": "hnsw",
          "space_type": "cosinesimil",
          "engine": "lucene"
        }
      },
      "price": {
        "type": "float"
      },
      "description": {
        "type": "text"
      },
      "category": {
        "type": "keyword"
      },
      "image_url": {
        "type": "text"
      },
      "rating": {
        "properties": {
          "rate": {
            "type": "float"
          },
          "count": {
            "type": "integer"
          }
        }
      }
    }
  }
}

Step 5: Ingest sample data

Use the following code to ingest the sample product data in Dev Tools.

POST /_bulk
{"index": {"_index": "product", "_id": "2"}}
{"id":2,"title":"Mens Casual Premium Slim Fit T-Shirts","price":22.3,"description":"Slim-fitting style, contrast raglan long sleeve, three-button henley placket, light weight & soft fabric for breathable and comfortable wearing.","category":"men's clothing","image":"https://fakestoreapi.com/img/71-3HjGNDUL._AC_SY879._SX._UX._SY._UY_.jpg","rating":{"rate":4.1,"count":259}}
{"index": {"_index": "product", "_id": "3"}}
{"id":3,"title":"Mens Cotton Jacket","price":55.99,"description":"great outerwear jackets for Spring/Autumn/Winter, suitable for many occasions, such as working, hiking, camping, mountain/rock climbing, cycling, traveling or other outdoors.","category":"men's clothing","image":"https://fakestoreapi.com/img/71li-ujtlUL._AC_UX679_.jpg","rating":{"rate":4.7,"count":500}}
{"index": {"_index": "product", "_id": "4"}}
{"id":4,"title":"Mens Casual Slim Fit","price":15.99,"description":"The color could be slightly different between on the screen and in practice.","category":"men's clothing","image":"https://fakestoreapi.com/img/71YXzeOuslL._AC_UY879_.jpg","rating":{"rate":2.1,"count":430}}
{"index": {"_index": "product", "_id": "5"}}
{"id":5,"title":"John Hardy Women's Legends Naga Gold & Silver Dragon Station Chain Bracelet","price":695,"description":"From our Legends Collection, the Naga was inspired by the mythical water dragon that protects the ocean's pearl.","category":"jewelery","image":"https://fakestoreapi.com/img/71pWzhdJNwL._AC_UL640_QL65_ML3_.jpg","rating":{"rate":4.6,"count":400}}

Step 6: Query the index

Run the following API call to test semantic search by using the Nova Multimodal Embeddings model.

GET /product/_search
{
  "_source": false,
  "fields": [
    "title",
    "price",
    "category",
    "image"
  ],
  "size": 3,
  "query": {
    "neural": {
      "title_vector": {
        "query_text": "jacket",
        "model_id": "<deployed model id>",
        "k": 5
      }
    }
  }
}

The output of the preceding query should look like the following.

{
  ...
  "hits": {
    "total": {
      "value": 4,
      "relation": "eq"
    },
    "max_score": 0.8333229,
    "hits": [
      {
        "_index": "product",
        "_id": "3",
        "_score": 0.8333229,
        "fields": {
          "image": [
            "https://fakestoreapi.com/img/71li-ujtlUL._AC_UX679_.jpg"
          ],
          "title": [
            "Mens Cotton Jacket"
          ],
          "category": [
            "men's clothing"
          ],
          "price": [
            55.99
          ]
        }
      }
      ...
    ]
  }
}

Step 7: Create an agent with Strands and Bedrock AgentCore Runtime

Now, create the Strands Agent that uses Anthropic Claude Sonnet 4.6 on Amazon Bedrock to search products from the OpenSearch Service index. To do so:

  • Import the Runtime app with from bedrock_agentcore.runtime import BedrockAgentCoreApp.
  • Initialize the app in your code with app = BedrockAgentCoreApp().
  • Create the OpenSearch Service connection and search query with the @tool decorator.
  • Decorate the invocation function with the @app.entrypoint decorator.
  • Let AgentCore Runtime control the running of the agent with app.run().

Now, complete the following steps:

  1. Make sure that you have installed the necessary dependencies from the Prerequisites section of this post.
  2. Create and save a file named search_agent.py with the following code. Replace <your hostname>, <your region>, and <your account id> placeholders within the code.
    from strands import Agent, tool
    import argparse
    import json
    from bedrock_agentcore.runtime import BedrockAgentCoreApp
    from strands.models import BedrockModel
    import boto3
    from opensearchpy import OpenSearch, RequestsHttpConnection
    from requests_aws4auth import AWS4Auth
    app = BedrockAgentCoreApp()
    @tool
    def search_products(query: str, size: int = 5):
    try:
    # OpenSearch configuration
    host = '' ## CHANGE THIS, DOMAIN ENDPOINT WITHOUT HTTPS!
    region = '' ##CHANGE THIS
    model_id= '' ##CHANGE THIS with your deployed model id in OpenSearch
    service = 'es'
    credentials = boto3.Session().get_credentials()
    awsauth = AWS4Auth(credentials.access_key, credentials.secret_key, region, service, session_token=credentials.token)
    # Create OpenSearch client
    client = OpenSearch(
    hosts=[{'host': host, 'port': 443}],
    http_auth=awsauth,
    use_ssl=True,
    verify_certs=True,
    connection_class=RequestsHttpConnection
    )
    """Search products in OpenSearch using neural search"""
    search_body = {
    "_source": False,
    "fields": ["title", "price", "category", "image"],
    "size": size,
    "query": {
    "neural": {
    "title_vector": {
    "query_text": query,
    "model_id": model_id,
    "k": 3
    }
    }
    }
    }
    response = client.search(
    body=search_body,
    index="product"
    )
    products = []
    for hit in response['hits']['hits']:
    fields = hit.get('fields', {})
    product = {
    'title': fields.get('title', [''])[0] if fields.get('title') else '',
    'price': fields.get('price', [''])[0] if fields.get('price') else '',
    'category': fields.get('category', [''])[0] if fields.get('category') else '',
    'image': fields.get('image', [''])[0] if fields.get('image') else ''
    }
    products.append(product)
    return f"Found {len(products)} products: {json.dumps(products, indent=2)}"
    except Exception as e:
    return f"Search error: {str(e)}"
    model_id = "global.anthropic.claude-haiku-4-5-20251001-v1:0"
    model = BedrockModel(
    model_id=model_id,
    )
    agent = Agent(
    model=model,
    tools=[search_products],
    system_prompt="You're a helpful assistant. You can do product search, and tell the product details."
    )
    @app.entrypoint
    def strands_agent_bedrock(payload):
    """
    Invoke the agent with a payload
    """
    user_input = payload.get("prompt")
    print("User input:", user_input)
    response = agent(user_input)
    return response.message['content'][0]['text']
    if __name__ == "__main__":
    #strands_agent_bedrock({"prompt": "Search jacket"}) ##UNCOMMENT THIS FOR TESTING
    #app.run() ##UNCOMMENT THIS FOR DEPLOYMENT, MAKE SURE THE ABOVE LINE IS COMMENTED WHEN YOU ARE DEPLOYING TO AGENTCORE

    This deploys your agent locally for testing purposes.

  3. Navigate to the IAM console and add the AmazonBedrockLimitedAccess permission policy to the principal running the code.
  4. Navigate to OpenSearch Dashboards and, from the left menu, choose Security plugin, then choose Roles.
  5. Choose Create Role.
  6. Name the role agentcore-permissions.
  7. Under cluster permissions, add cluster:admin/opensearch/ml/models/get and cluster:admin/opensearch/ml/predict.
  8. Under index permissions, enter product* as the index pattern. Add search and get permissions.
  9. Create the role.
  10. Choose the role you created, switch to the Mapped Users tab, choose Manage mapping, and add the role that you use for running the Python code as a backend role.
  11. Uncomment the line strands_agent_bedrock({"prompt": "Search jacket"}) and make sure the app.run() line is commented in the code.
  12. Run python search_agent.py in your terminal to start the shopping agent. The output should look similar to the following.
    "Here are the jacket search results:\n\n1. **Mens Cotton Jacket** - $55.99\n2. **Mens Casual Slim Fit** - $15.99\n3. **Mens Casual Premium Slim Fit T-Shirts** - $22.30\n4. **John Hardy Women's Legends Naga Gold & Silver Dragon Station Chain Bracelet** - $695.00\n\nThe most relevant jacket option is the **Mens Cotton Jacket** at $55.99. Would you like to know more about any of these products?

  13. Comment strands_agent_bedrock({"prompt": "Search jacket"}) and uncomment the app.run() line in the code before going into the next step.

Step 8: Configure and launch your agent to Bedrock AgentCore Runtime

The AgentCore CLI is a command-line tool provided by AWS that simplifies deployment of agents to Amazon Bedrock AgentCore Runtime. When you run the CLI deployment command, it automates the entire deployment workflow: it creates the necessary IAM execution role with proper permissions, packages your Python application code along with its dependencies, uses AWS CodeBuild to build an optimized Docker container image, pushes that container image to Amazon Elastic Container Registry (ECR), and finally provisions the AgentCore Runtime environment that hosts your containerized agent. This eliminates the need for manual Dockerfile creation, container builds, or infrastructure management.

  1. Before you start this step, make sure you have gone through section 7 and installed the AgentCore CLI and Python dependencies listed in the Prerequisites section.
  2. Create a policy named AgentCoreAccessPolicy with the following permissions and attach it to the role running the code. Replace <ACCOUNT_ID> and <REGION> placeholders.
{
  "Version": "2012-10-17",
  "Statement": [
    {
      "Sid": "BedrockAgentCoreServiceAccess",
      "Effect": "Allow",
      "Action": [
        "bedrock-agentcore:*"
      ],
      "Resource": "*"
    },
    {
      "Sid": "ECRAuthorizationToken",
      "Effect": "Allow",
      "Action": [
        "ecr:GetAuthorizationToken"
      ],
      "Resource": "*"
    },
    {
      "Sid": "ECRRepositoryAccess",
      "Effect": "Allow",
      "Action": [
        "ecr:BatchCheckLayerAvailability",
        "ecr:GetDownloadUrlForLayer",
        "ecr:BatchGetImage",
        "ecr:PutImage",
        "ecr:InitiateLayerUpload",
        "ecr:UploadLayerPart",
        "ecr:CompleteLayerUpload",
        "ecr:DescribeRepositories",
        "ecr:CreateRepository",
        "ecr:ListImages",
        "ecr:DescribeImages"
      ],
      "Resource": [
        "arn:aws:ecr:<REGION>:<ACCOUNT_ID>:repository/bedrock-agentcore-*"
      ]
    },
    {
      "Sid": "CodeBuildProjectAccess",
      "Effect": "Allow",
      "Action": [
        "codebuild:CreateProject",
        "codebuild:UpdateProject",
        "codebuild:StartBuild",
        "codebuild:BatchGetBuilds",
        "codebuild:DeleteProject"
      ],
      "Resource": "*"
    },
    {
      "Sid": "IAMRoleManagement",
      "Effect": "Allow",
      "Action": [
        "iam:CreateRole",
        "iam:AttachRolePolicy",
        "iam:PutRolePolicy",
        "iam:GetRole",
        "iam:GetRolePolicy",
        "iam:PassRole",
        "iam:DeleteRole",
        "iam:DeleteRolePolicy",
        "iam:DetachRolePolicy",
        "iam:CreateServiceLinkedRole"
      ],
      "Resource": [
        "arn:aws:iam::<ACCOUNT_ID>:role/BedrockAgentCoreExecutionRole-*",
        "arn:aws:iam::<ACCOUNT_ID>:role/AmazonBedrockAgentCoreSDKCodeBuild-*",
        "arn:aws:iam::<ACCOUNT_ID>:role/aws-service-role/runtime-identity.bedrock-agentcore.amazonaws.com/AWSServiceRoleForBedrockAgentCoreRuntimeIdentity"
      ]
    },
    {
      "Sid": "CloudWatchLogsAccess",
      "Effect": "Allow",
      "Action": [
        "logs:CreateLogGroup",
        "logs:CreateLogStream",
        "logs:PutLogEvents",
        "logs:PutResourcePolicy"
      ],
      "Resource": "arn:aws:logs:<REGION>:<ACCOUNT_ID>:log-group:/aws/bedrock-agentcore/*"
    },
    {
      "Sid": "CloudWatchLogsResourcePolicy",
      "Effect": "Allow",
      "Action": [
        "logs:PutResourcePolicy"
      ],
      "Resource": "*"
    },
    {
      "Sid": "S3BucketManagement",
      "Effect": "Allow",
      "Action": [
        "s3:CreateBucket",
        "s3:PutBucketPolicy",
        "s3:PutBucketVersioning",
        "s3:PutBucketPublicAccessBlock",
        "s3:PutLifecycleConfiguration",
        "s3:PutObject",
        "s3:GetObject",
        "s3:ListBucket"
      ],
      "Resource": [
        "arn:aws:s3:::bedrock-agentcore-codebuild-sources-<ACCOUNT_ID>-*",
        "arn:aws:s3:::bedrock-agentcore-codebuild-sources-<ACCOUNT_ID>-*/*"
      ]
    }
  ]
}
  1. Create a file named agentcore.yaml in your project directory with the following configuration. Replace <REGION>, <ACCOUNT_ID>, and <OPENSEARCH_DOMAIN_NAME> placeholders:
# AgentCore Runtime Configuration
  runtime:
    name: shopping-search-agent-runtime
    entrypoint: search_agent.py:strands_agent_bedrock
    region: <REGION>  # CHANGE THIS - Your AWS region (e.g., us-east-1)

    execution_role:
      create: true
      name: BedrockAgentCoreExecutionRole-shopping-agent
      policies:
        - policy_name: BedrockAndOpenSearchAccess
          policy_document:
            Version: "2012-10-17"
            Statement:
              - Sid: BedrockModelAccess
                Effect: Allow
                Action:
                  - bedrock:InvokeModel
                  - bedrock:InvokeModelWithResponseStream
                Resource:
                  - arn:aws:bedrock:*::foundation-model/*
                  - arn:aws:bedrock:<REGION>:<ACCOUNT_ID>:inference-profile/*  # CHANGE THIS - Replace <REGION> and <ACCOUNT_ID>
              - Sid: OpenSearchAccess
                Effect: Allow
                Action:
                  - es:ESHttpGet
                  - es:ESHttpPost
                  - es:ESHttpPut
                Resource: arn:aws:es:<REGION>:<ACCOUNT_ID>:domain/<OPENSEARCH_DOMAIN_NAME>/*  # CHANGE THIS - Replace all three placeholders
              - Sid: CloudWatchLogsAccess
                Effect: Allow
                Action:
                  - logs:CreateLogGroup
                  - logs:CreateLogStream
                  - logs:PutLogEvents
                Resource: arn:aws:logs:<REGION>:<ACCOUNT_ID>:log-group:/aws/bedrock-agentcore/runtimes/*  # CHANGE THIS - Replace <REGION> and <ACCOUNT_ID>
              - Sid: ECRImageAccess
                Effect: Allow
                Action:
                  - ecr:GetAuthorizationToken
                  - ecr:BatchGetImage
                  - ecr:GetDownloadUrlForLayer
                Resource: "*"

    container:
      architecture: arm64  # Options: arm64 or x86_64
      requirements_file: requirements.txt

    ecr:
      auto_create: true
  1. Run the following command in your terminal to deploy the agent to AgentCore Runtime:
    • Create the AgentCore project and replace with your search agent.
      agentcore create --name ShoppingAgent --defaults
      cd ShoppingAgent
      cp ../search_agent.py app/ShoppingAgent/main.py

    • Add OpenSearch and other dependencies:
      cd app/ShoppingAgent
      uv add opensearch-py requests-aws4auth boto3
      cd ../..

    • Deploy the agent to Agentcore Runtime. This process takes approximately 5-10 minutes.
      agentcore deploy

    • Once deployment completes, verify the runtime status:
      agentcore status

      You should see:

      ShoppingAgent: Deployed - Runtime: READY (arn:aws:bedrock-agentcore:<REGION>:<ACCOUNT_ID>:runtime/ShoppingAgent_...)
      
      URL: https://bedrock-agentcore.<REGION>.amazonaws.com/runtimes/.../invocations

Step 9: Configure OpenSearch Service access

Map your AgentCore execution role to an OpenSearch backend role so the agent can access your data.

  1. Navigate to OpenSearch Dashboards. From the left menu, choose the Security plugin, then choose Roles.
  2. Search for agentcore-permissions and choose the role. Then, navigate to the Mapped Users tab, choose Manage mapping, and add arn:aws:iam::<ACCOUNT_ID>:role/AmazonBedrockAgentCoreSDKRuntime-us-east-1-custom as a backend role. Replace the <ACCOUNT_ID> placeholder with your account ID.

Animated demo of OpenSearch Dashboards Security plugin showing the agent-permissions role with the Mapped Users tab open and the AgentCore SDK runtime IAM role added as a backend role.

Step 10: Invoke the Bedrock AgentCore Runtime

You can test the agent in Agent Sandbox. Enter the prompt Search jacket less than 50$, and the agent returns the relevant result from the OpenSearch Service index with a summary.

Agent Sandbox console showing a shopping agent response that returns the Mens Cotton Jacket as the relevant result for the prompt “Search jacket less than 50$”.

In real-world scenarios, you can design a search application with a Strands Agent deployed in AgentCore Runtime. You can add AgentCore Memory, which gives your AI agents the ability to remember past interactions and provide more context-aware, personalized conversations.

Cleanup

To avoid incurring future charges, delete the resources created while building this solution:

  1. Delete the OpenSearch Service domain.
  2. Delete the Amazon Bedrock AgentCore Runtime resources.

Conclusion

In this post, you saw how to create a conversational search with Amazon OpenSearch Service and Strands Agents. You also learned how to deploy the agent on Amazon Bedrock AgentCore Runtime. You can further enhance this shopping agent by using other AgentCore capabilities. For example, AgentCore Memory retains user preferences and past interactions across sessions, AgentCore Identity manages shopper authentication and access control, and AgentCore Observability helps you monitor and debug agent behavior in production. Together, these services help you build shopping experiences that deliver instant, relevant assistance at scale.

Now it’s your turn. Build your own conversational search experience by integrating OpenSearch Service and Strands Agents with your product catalog. To learn more, see the Amazon OpenSearch Service and Amazon Bedrock AgentCore detail pages.


About the authors

Omama Khurshid

Omama Khurshid

Omama is an GTM Specialist Solutions Architect Analytics at Amazon Web Services. She focuses on helping customers across various industries build reliable, scalable, and efficient solutions. Outside of work, she enjoys spending time with her family, listening to music, and learning new technologies.

Jumana Nagaria

Jumana Nagaria

Jumana is a Prototyping Architect at AWS. She builds innovative prototypes with customers to solve their business challenges. She is passionate about cloud computing and data analytics. Outside of work, Jumana enjoys travelling, reading, painting, and spending quality time with friends and family.

Canberk Keles

Canberk Keles

Canberk is a Solutions Architect at Amazon Web Services, helping software companies achieve their business goals by leveraging AWS technologies. He is part of OpenSearch specialist community within AWS and has been guiding customers harness the power of OpenSearch. Outside of work, he enjoys sports, reading, traveling and playing video games.

AWS Weekly Roundup: BYOM for Amazon RDS for SQL Server, AWS IoT Device SDK for Swift, and more (June 8, 2026)

Post Syndicated from Sébastien Stormacq original https://aws.amazon.com/blogs/aws/aws-weekly-roundup-byom-for-amazon-rds-for-sql-server-aws-iot-device-sdk-for-swift-and-more-june-8-2026/

This week, the AWS IoT Device SDK for Swift reached general availability. As a member of the Swift Server Workgroup (SSWG), this one caught my attention. The SDK brings production-ready MQTT 5 connectivity, Device Shadow, Jobs, and fleet provisioning to Swift developers on macOS, iOS, tvOS, and Linux.

Swift on IoT and Edge devices, an AI generated illustration

I’m curious to see what you will build with it. Swift on the server has matured over the past few years, and now it reaches IoT devices too. This connects to a broader trend of running Swift at the edge. WendyOS, for example, is an open-source operating system for physical AI that offers first-class Swift support for deploying apps to NVIDIA Jetson and Raspberry Pi hardware. Between server-side Swift, IoT, and edge computing, the language is showing up in places that would have surprised most people a few years ago.

Now, let’s get into this week’s AWS news.

Headlines
Amazon RDS for SQL Server supports Bring Your Own Media — Customers who migrate SQL Server applications from on-premises environments can now reuse their existing Microsoft SQL Server licenses, including Software Assurance, through Microsoft’s License Mobility program on Amazon RDS. BYOM is integrated with AWS License Manager for tracking license usage and compliance. Read more.

Amazon Cognito now supports multi-Region replication — You can now synchronize user and machine identity data, including credentials, user pool configurations, and federation setups, to a secondary user pool in a standby Region in near real-time. In the event of a disruption in the primary Region, signed-in users continue accessing their applications without re-authenticating, and registered users can sign in with their existing credentials. Multi-Region replication is available as an add-on for user pools in Essentials or Plus feature tiers across 16 Regions. Read more.

GPT-5.5, GPT-5.4, and Codex from OpenAI are now generally available on Amazon Bedrock — You can now use GPT-5.5 and GPT-5.4 in production workloads on Amazon Bedrock and build with Codex for AI-powered software development, with the same security, governance, and operational controls you already use across AWS. GPT-5.5 is the most capable model from OpenAI, excelling at agentic coding, data analysis, and multi-step autonomous tasks. Codex is available through the Codex App, the Codex CLI, and IDE integrations with Visual Studio Code, JetBrains, and Xcode. Pricing matches OpenAI first-party rates, and usage counts toward existing AWS commitments. Read more.

Last week’s launches
Here are some launches and updates from this past week that caught my attention:

For a full list of AWS announcements, be sure to keep an eye on the What’s New with AWS page.

Upcoming AWS events
Learn more about AWS, browse and join upcoming AWS-led in-person and virtual events, startup events, and developer-focused events as well as AWS Summits and AWS Community Days. Join the AWS Builder Center to connect with builders, share solutions, and access content that supports your development.

That’s all for this week. Check back next Monday for another Weekly Roundup!

— seb

Secure multi-tenant AI agents with Amazon Bedrock AgentCore resource-based policies

Post Syndicated from Satyen Verma original https://aws.amazon.com/blogs/security/secure-multi-tenant-ai-agents-with-amazon-bedrock-agentcore-resource-based-policies/

Software as a service (SaaS) providers building AI-powered applications on Amazon Bedrock AgentCore often need to serve multiple tenants with distinct security requirements from a shared infrastructure. Some tenants require cross-account access from their own Amazon Web Services (AWS) accounts, while others mandate that traffic stay within a private virtual private cloud (VPC) for regulatory compliance. Without centralized resource-level control, managing these diverse requirements can be complex.

AgentCore supports resource-based policies, giving you centralized, resource-level control over who can access your AgentCore Runtime and AgentCore Runtime endpoint resources and under what conditions.

In this post, you walk through a multi-tenant AI customer service platform where two tenants need different levels of access to the same agent. You learn how to use resource-based policies on AgentCore to grant cross-account access for one tenant while restricting another to VPC-only traffic—all while sharing the same underlying AgentCore Runtime and AgentCore Runtime endpoint.

The multi-tenant scenario

Imagine you’re an SaaS provider who builds and operates an AI-powered customer service platform. You use AgentCore to deploy intelligent agents that handle customer inquiries, answering product questions, processing returns, and escalating complex issues to human agents.

You serve multiple enterprise clients (tenants), each with their own AWS account and unique security requirements:

  • Tenant A: Example Corp is a large retailer operating in AWS account 111122223333. Their development team is building a customer-facing chat agent that calls your AI agent to answer product questions in real time, and their admin team needs access to test agent behavior and monitor responses. Both roles must invoke the agent directly from Example Corp’s own AWS account without you having to share credentials or create AWS Identity and Access Management (IAM) users on their behalf. Example Corp has no network restriction requirements—their teams can invoke the agent from any network path as long as they have valid AWS credentials.
  • Tenant B: AnyCompany is a healthcare company operating in AWS account 444455556666. Because of regulatory (HIPAA) requirements, AI agent traffic must originate only from their private VPC (vpc-health1234). Their internal support staff uses the AI agent to assist with patient billing inquiries, which might involve protected health information (PHI). Their compliance team mandates that no API call to the agent can be made from developer laptops, public endpoints, or any network outside the controlled VPC boundary.
  • Your platform (SaaS provider) runs in account 555555555555 in the us-west-2 AWS Region. You operate an AgentCore Runtime (support-agent-runtime) that handles the core customer service logic, and an AgentCore Runtime endpoint (DEFAULT) that routes requests to the latest version of the support agent. Both tenants share this same agent infrastructure.

You can use resource-based policies to define who can access your AgentCore Runtime and AgentCore Runtime endpoint directly on the resources themselves—centralizing access control on the resource side. For cross-account scenarios like Example Corp, both a resource-based policy on your resources and an identity-based policy in the tenant’s account are required. For VPC-restricted scenarios like AnyCompany, you can use specific IAM conditions to enforce that requests originate only from an approved VPC, adding a network-level security boundary on top of identity-based controls.

Solution architecture

The following diagram shows the architecture for the multi-tenant AI customer service platform with both access patterns.

Figure 1: Architecture for the multi-tenant AI customer service platform with both access patterns

Figure 1: Architecture for the multi-tenant AI customer service platform with both access patterns

  • Your account (555555555555) with AgentCore Runtime and AgentCore Runtime endpoint
  • Example Corp’s account (111122223333) with DeveloperRole and AdminRole
  • AnyCompany’s account (444455556666) with VPC boundary and ApplicationRole
  • Policy enforcement points on both resources
  • VPC endpoint in AnyCompany’s VPC connecting to AgentCore

The SaaS provider account (555555555555) hosts the AgentCore Runtime and AgentCore Runtime endpoint that both tenants share. Example Corp (111122223333) accesses the agent cross-account using IAM roles—DeveloperRole and AdminRole—authenticated with Signature Version 4 (SigV4), the standard AWS request signing protocol. AWS evaluates both the resource-based policy on your resources and the identity-based policy in Example Corp’s account before granting access.

AnyCompany (444455556666) also accesses the agent cross-account, but with an additional constraint: all requests must originate from within their private VPC (vpc-health1234) through a VPC endpoint for AgentCore. The resource-based policy on your resources includes an explicit Deny statement that blocks any request from AnyCompany’s ApplicationRole when it doesn’t originate from the approved VPC.

In both cases, resource-based policies must be applied to both the AgentCore Runtime and AgentCore Runtime endpoint. AWS evaluates policies on both resources for InvokeAgentRuntime operations—if either resource denies access or lacks an explicit Allow, the request is denied.

Prerequisites

Before you begin, ensure you have the following:

  • An AWS account with AgentCore access and permissions to call PutResourcePolicy, GetResourcePolicy, and DeleteResourcePolicy on AgentCore resources
  • AWS Command Line Interface (AWS CLI) v2 installed and configured with the bedrock-agentcore-control API available
  • An AgentCore Runtime with SigV4 authentication and a DEFAULT AgentCore Runtime endpoint pointing to the latest runtime version

For the VPC-restricted scenario, the tenant must have a VPC endpoint for AgentCore configured in their VPC. An interface VPC endpoint creates a private connection between the tenant’s VPC and the AgentCore service without requiring traffic to traverse the public internet. For more information, see Interface VPC endpoints for Amazon Bedrock AgentCore.

Implementation

Both Example Corp and AnyCompanyoperate in separate AWS accounts from your platform. For cross-account access to AgentCore Runtime, AWS requires that both of the following allow the action:

  • A resource-based policy in your platform account applied to both the AgentCore Runtime and its AgentCore Runtime endpoint. InvokeAgentRuntime operations require an explicit Allow on both resources—if either lacks one, the request is denied.
  • An identity-based policy attached to the caller’s IAM role in the tenant’s account.

If either side is missing or denies the action, the request is denied.

Step 1: Configure cross-account access for Example Corp (Tenant A)

Example Corp’s DeveloperRole and AdminRole in account 111122223333 need to invoke your AI customer service agent. Without resource-based policies, enabling this cross-account access would typically require Example Corp’s roles to assume a role in your platform account through IAM role chaining—adding operational complexity, introducing temporary credential management, and creating additional IAM roles that must be maintained in your account for each tenant. With resource-based policies, you grant Example Corp’s roles direct access to your AgentCore Runtime and AgentCore Runtime endpoint without role chaining. Example Corp’s roles can invoke the agent directly from their own account using their own credentials, while you maintain centralized control over access on the resource side.

AgentCore Runtime resource-based policy

The following policy grants Example Corp’s DeveloperRole and AdminRole permission to invoke the agent runtime. This is the first of two resource-based policies required—it controls access to the runtime resource itself. Save this as runtime-policy.json:

{
  "Version": "2012-10-17",
  "Statement": [
    {
      "Sid": "AllowExampleCorpCrossAccountAccess",
      "Effect": "Allow",
      "Principal": {
        "AWS": [
          "arn:aws:iam::111122223333:role/DeveloperRole",
          "arn:aws:iam::111122223333:role/AdminRole"
        ]
      },
      "Action": "bedrock-agentcore:InvokeAgentRuntime",
      "Resource": "arn:aws:bedrock-agentcore:us-west-2:555555555555:runtime/support-agent-runtime"
    }
  ]
}

AgentCore Runtime endpoint resource-based policy

The following policy grants the same roles permission to invoke the AgentCore Runtime endpoint. Without this second policy, requests are allowed at the runtime level but denied at the endpoint level, and the invocation fails. Save this as endpoint-policy.json:

{
    "Version": "2012-10-17",
    "Statement": [
        {
            "Sid": "AllowExampleCorpCrossAccountAccess",
            "Effect": "Allow",
            "Principal": {
                "AWS": [
                    "arn:aws:iam::111122223333:role/DeveloperRole",
                    "arn:aws:iam::111122223333:role/AdminRole"
                ]
            },
            "Action": "bedrock-agentcore:InvokeAgentRuntime",
            "Resource": "arn:aws:bedrock-agentcore:us-west-2:999999999999:runtime/support-agent-runtime/runtime-endpoint/DEFAULT"
        }
    ] 
}

To apply the resource-based policies

aws bedrock-agentcore-control put-resource-policy \--resource-arn arn:aws:bedrock-agentcore:us-west-2:555555555555:runtime/support-agent-runtime \--policy file://runtime-policy.json \--region us-west-2
aws bedrock-agentcore-control put-resource-policy \--resource-arn arn:aws:bedrock-agentcore:us-west-2:555555555555:runtime/support-agent-runtime/runtime-endpoint/DEFAULT \--policy file://endpoint-policy.json \--region us-west-2

To verify the resource-based policies

aws bedrock-agentcore-control get-resource-policy \--resource-arn arn:aws:bedrock-agentcore:us-west-2:555555555555:runtime/support-agent-runtime \--region us-west-2
aws bedrock-agentcore-control get-resource-policy \--resource-arn arn:aws:bedrock-agentcore:us-west-2:555555555555:runtime/support-agent-runtime/runtime-endpoint/DEFAULT \--region us-west-2

Configure an identity-based policy (Example Corp’s account)

Resource-based policies alone aren’t sufficient for cross-account access. Example Corp must also attach an identity-based policy to DeveloperRole and AdminRole in their account (111122223333) that allows the same action on your resources. Without this policy on the tenant side, IAM denies the cross-account request even though your resource-based policies allow it.

Example Corp attaches the following policy to both DeveloperRole and AdminRole:

{
    "Version": "2012-10-17",
    "Statement": [
        {
            "Sid": "AllowInvokeAgentRuntime",
            "Effect": "Allow",
            "Action": "bedrock-agentcore:InvokeAgentRuntime",
            "Resource": [
                "arn:aws:bedrock-agentcore:us-west-2:555555555555:runtime/support-agent-runtime",
                "arn:aws:bedrock-agentcore:us-west-2:555555555555:runtime/support-agent-runtime/runtime-endpoint/DEFAULT"
            ]
        }
    ] 
}

Attach this policy to both DeveloperRole and AdminRole in Example Corp’s account.

Step 2: Configure cross-account with VPC-restricted access for AnyCompany (Tenant B)

AnyCompany operates under HIPAA compliance requirements and mandates that all traffic to your agent stays within a private network path. Like Example Corp, AnyCompany needs cross-account access from account 444455556666—but with an additional constraint, requests must originate from their VPC vpc-health1234 through an interface VPC endpoint. Any request from outside this VPC is denied, even if it comes from AnyCompany’s ApplicationRole.

Resource-based policies (your platform account): To enforce this, you update the resource-based policies on both the AgentCore Runtime and AgentCore Runtime endpoint. Each policy includes an Allow statement that grants ApplicationRole permission to invoke the agent, paired with a Deny statement that blocks any request not originating from vpc-health1234. In the following policy, the Deny statement uses StringNotEquals on aws:SourceVpc . When a request arrives through an interface VPC endpoint, AWS populates this key with the VPC ID. If it doesn’t match vpc-health1234, or if the key is absent because no VPC endpoint was used, the Deny takes effect. Because an explicit Deny overrides any Allow from any policy, this pattern helps ensure that no other identity-based or resource-based policy can inadvertently grant AnyCompany access from outside the VPC. Add the following statements to runtime-policy-v2.json alongside the Example Corp statement from Step 1:

{
  "Sid": "AllowAnyCompanyCrossAccountAccess",
  "Effect": "Allow",
  "Principal": {
    "AWS": "arn:aws:iam::444455556666:role/ApplicationRole"
  },
  "Action": "bedrock-agentcore:InvokeAgentRuntime",
  "Resource": "arn:aws:bedrock-agentcore:us-west-2:555555555555:runtime/support-agent-runtime"
},
{
  "Sid": "DenyAnyCompanyOutsideVpc",
  "Effect": "Deny",
  "Principal": {
    "AWS": "arn:aws:iam::444455556666:role/ApplicationRole"
  },
  "Action": "bedrock-agentcore:InvokeAgentRuntime",
  "Resource": "arn:aws:bedrock-agentcore:us-west-2:555555555555:runtime/support-agent-runtime",
  "Condition": {
    "StringNotEquals": {
      "aws:SourceVpc": "vpc-health1234"
    }
  }
}

AgentCore Runtime endpoint resource-based policy

Add the equivalent statement to endpoint-policy-v2.json:

{
    "Sid": "AllowAnyCompanyCrossAccountAccess",
    "Effect": "Allow",
    "Principal": {
        "AWS": "arn:aws:iam::444455556666:role/ApplicationRole"
    },
    "Action": "bedrock-agentcore:InvokeAgentRuntime",
    "Resource": "arn:aws:bedrock-agentcore:us-west-2:555555555555:runtime/support-agent-runtime/runtime-endpoint/DEFAULT"
},
{
    "Sid": "DenyHealthFirstOutsideVpc",
    "Effect": "Deny",
    "Principal": {
        "AWS": "arn:aws:iam::444455556666:role/ApplicationRole"
    },
    "Action": "bedrock-agentcore:InvokeAgentRuntime",
    "Resource": "arn:aws:bedrock-agentcore:us-west-2:555555555555:runtime/support-agent-runtime/runtime-endpoint/DEFAULT",
    "Condition": {
        "StringNotEquals": {
            "aws:SourceVpc": "vpc-health1234"
        }
    }
}

Because put-resource-policy replaces the entire policy on a resource, your updated policy files must include both the preceding AnyCompany statments and the Example Corp statements from Step 1.

Apply the updated resource-based policies

aws bedrock-agentcore-control put-resource-policy \
	--resource-arn arn:aws:bedrock-agentcore:us-west-2:555555555555:runtime/support-agent-runtime \
	--policy file://runtime-policy-v2.json \
	--region us-west-2 

aws bedrock-agentcore-control put-resource-policy \
	--resource-arn arn:aws:bedrock-agentcore:us-west-2:555555555555:runtime/support-agent-runtime/runtime-endpoint/DEFAULT \
	--policy file://endpoint-policy-v2.json \
	--region us-west-2

Verify the updated policies

After applying the final policies, verify them using the get-resource-policy command:

# Verify Agent Runtime policy 
aws bedrock-agentcore-control get-resource-policy \
	--resource-arn arn:aws:bedrock-agentcore:us-west-2:555555555555:runtime/support-agent-runtime \
	--region us-west-2 

# Verify Agent Runtime Endpoint policy 
aws bedrock-agentcore-control get-resource-policy \
	--resource-arn arn:aws:bedrock-agentcore:us-west-2:555555555555:runtime/support-agent-runtime/runtime-endpoint/DEFAULT \
	--region us-west-2

Identity-based policy (AnyCompany’s account)

AnyCompany must attach an identity-based policy to ApplicationRole in their account 444455556666 that allows the same InvokeAgentRuntime on your resources in account 555555555555. Without this policy on the tenant side, IAM denies the cross-account request even though your resource-based policies allow it.

AnyCompany attaches the following policy to ApplicationRole:

{
    "Version": "2012-10-17",
    "Statement": [
        {
            "Sid": "AllowInvokeAgentRuntime",
            "Effect": "Allow",
            "Action": "bedrock-agentcore:InvokeAgentRuntime",
            "Resource": [
                "arn:aws:bedrock-agentcore:us-west-2:555555555555:runtime/support-agent-runtime",
                "arn:aws:bedrock-agentcore:us-west-2:555555555555:runtime/support-agent-runtime/runtime-endpoint/DEFAULT"
            ]
        }
    ] 
}

The VPC restriction is enforced entirely on resource account through the resource-based policy condition, AnyCompany’s identity-based policy doesn’t need VPC conditions. This keeps the tenant-side configuration straightforward while you maintain centralized network-level control.

OAuth authentication considerations

The policies in this post use SigV4 authentication with specific IAM role principals. If your AgentCore Runtime or AgentCore Gateway is configured with OAuth authentication instead, the principal structure changes. OAuth-authenticated resources require a wildcard principal (“Principal": "*") because the caller identity comes from a JSON Web Token (JWT) validated before policy evaluation. Anonymous or unauthenticated requests are rejected before the policy is evaluated, so the wildcard principal doesn’t grant open access. To restrict OAuth-authenticated requests to a specific VPC, combine the wildcard principal with a VPC condition in the resource-based policy. IAM principal-based condition keys such as aws:PrincipalAccount and aws:PrincipalOrgID aren’t populated in the OAuth authentication context—only supported network-level condition keys (such as aws:SourceVpc, aws:SourceVpce, aws:SourceIp) are available for use in resource-based policies with OAuth. For more details, see Resource-based policies for Amazon Bedrock AgentCore.

Understanding policy evaluation

To understand how AWS evaluates these policies when a request arrives, consider the following scenarios:

Caller or principal Network Identity-based policy (tenant side) Runtime resource-based policy Runtime endpoint resource-based policy Final policy evaluation result
Example Corp Any network Allows Allows Allows Allowed
Example Corp Any network Allows Allows Allows Allowed
AnyCompany From Allows Allows ( does not match) Allows ( does not match) Allowed
AnyCompany Outside VPC Allows matches matches Denied
Any other cross-account role Any network Allows No matching No matching Denied
Any other cross-account role Any network No policy Allows Allows Denied

Conclusion and next steps

In this post, you learned how to use resource-based policies on AgentCore to secure a multi-tenant AI platform with distinct access patterns for each tenant:

  • Example Corp gets seamless cross-account integration, their development and admin teams can invoke your AI agent directly from their own AWS account without credential management.
  • AnyCompany gets the strict network-level isolation their compliance team requires, the AI agent is accessible only from within their private VPC, ensuring that interactions involving potential PHI — stay within the controlled network boundary

Both tenants share the same underlying AgentCore Runtime and AgentCore Runtime endpoint, yet each has tailored security controls enforced at the resource level. his approach avoids per-tenant infrastructure duplication while satisfying each tenant’s security posture, a challenge you likely face when onboarding tenants with different compliance postures. Resource-based policies complement identity-based IAM policies, giving you layered control over which principals can invoke which agents, and from which network paths.

Next steps

If you have feedback about this post, submit comments in the Comments section below.


Satyen Verma

Satyen Verma

Satyen is a Software Engineer at AWS building secure and scalable runtime systems for Amazon Bedrock AgentCore. He focuses on enabling reliable, high-performance agentic AI applications for customers worldwide.

Zohreh Norouzi

Zohreh Norouzi

Zohreh is a Security Solutions Architect at AWS. She helps customers make good security choices and accelerate their journey to the AWS Cloud. She has been actively involved in generative AI security initiatives across APJ, using her expertise to help customers build secure generative AI solutions at scale.

Vijay Kumar Samanthapudi

Vijay Kumar Samanthapudi

Vijay is a Software Engineer at AWS building secure and scalable runtime systems for Amazon Bedrock AgentCore. He focuses on enabling reliable, high-performance agentic AI applications for customers worldwide.

Satveer Khurpa

Satveer Khurpa

Satveer is a Sr. WW Specialist Solutions Architect, Amazon Bedrock AgentCore at AWS, specializing in agentic AI security with a focus on AgentCore Identity and Security. He uses his expertise in cloud-based architectures to help clients design and deploy secure agentic AI systems across diverse industries.

Prajit Pabbati

Prajit Pabbati

Prajit is a Software Development Manager at AWS building secure and scalable runtime systems for Amazon Bedrock AgentCore.

Why Policy in Amazon Bedrock AgentCore chose Cedar for securing agentic workflows

Post Syndicated from Liana Hadarean original https://aws.amazon.com/blogs/security/why-policy-in-amazon-bedrock-agentcore-chose-cedar-for-securing-agentic-workflows/

Agents have agency: they adapt and find multiple ways to solve problems. This autonomy creates a fundamental security challenge: the large language model (LLM) at the heart of the agent is non-deterministic, and its decisions can’t be predicted or guaranteed in advance. It can hallucinate harmful actions with complete confidence. It’s vulnerable to prompt injection attacks, where adversaries inject malicious commands through tool responses or user inputs. LLMs don’t robustly differentiate between commands and data, everything is only tokens. For these reasons, if you want defense in depth, you must treat the LLM as an untrusted actor from a security point of view.

The insight is that the LLM can’t affect the external world directly: it has to go through an orchestrator that invokes tools based on the LLM’s output. This is precisely where the controls must be applied. What you need at this boundary is authorization: a decision about whether each tool invocation should be allowed and under what conditions. Consider a customer service agent for an online retailer. Without proper controls, it could process refunds that exceed authorized limits, apply discounts to product categories that should be excluded, or look up one customer’s data while handling another customer’s session.

If you control agents’ access to tools, you can establish a safety envelope within which the agent can operate freely. This differs from two common but unsatisfactory approaches:

  • Creating hard-coded workflows eliminates uncertainty, but by itself defeats the purpose of using an LLM as the brain of the agent, because you’ve built a traditional application with an LLM interface. And even with this restriction, using LLM outputs at any step can open up the same risks. While it’s a useful technique for well-understood workflows, it’s not sufficient for agents that need to adapt.
  • Human-in-the-loop provides a safety net for critical operations, and it will always have a role. But relying on it as the main control mechanism sacrifices autonomy and can lead to approval fatigue.

You need agents that are safe and autonomous. This requires an auditable, deterministic enforcement layer that sits outside the agent and tools. Why outside? Because the LLM’s plan is the thing you can’t trust—it can’t be responsible for enforcing its own constraints. Controls at the LLM layer—such as system prompts and training-time alignment—can be bypassed by prompt injection or hallucination. Hard-coded checks in agent or tool code are more robust, but become difficult to audit and manage at scale, especially when security logic is scattered across many tools and services. Centralizing authorization outside both gives you a single checkpoint the LLM can’t circumvent; one that’s auditable and can be verified independently of the application code.

This is where AgentCore Policies come in. Amazon Bedrock AgentCore Gateway sits between the agent and the remote tools it calls. When you associate a Policy with a Gateway, it blocks everything by default. Policies selectively open this boundary by specifying which tool invocations are allowed and under what conditions. This enforcement applies to all tool traffic routed through the Gateway. For this approach to scale, it must be more straightforward to reason about the policies than about the agent’s behavior.

AgentCore policies are expressed in Cedar. Cedar is an open source authorization policy language developed by AWS that has recently joined the Cloud Native Computing Foundation (CNCF). Cedar was designed with exactly these properties: it’s purpose-built for authorization, readable by humans, and analyzable by machines using automated reasoning. This gives enterprises the ability to scale policy definition and enforcement to their AI agents.

How Cedar is used by Amazon Bedrock AgentCore

Amazon Bedrock AgentCore provides the infrastructure to deploy and manage agents at scale. It includes AgentCore Runtime for hosting agents, AgentCore Gateway for managing how agents connect to tools using Model Context Protocol (MCP), and Policy in AgentCore. Policy intercepts all agent traffic through AgentCore gateways and evaluates each request against defined policies in the policy engine before allowing tool access. Cedar powers the policy layer.

AgentCore Policy uses Cedar and its mathematical analysis capabilities at several points in the AgentCore Gateway workflow: the Cedar authorization engine is used at policy evaluation and Cedar Analysis is used during policy authoring, and in the control plane.

Policy authoring: Developers can write Cedar policies directly or use natural language that gets translated to Cedar through a neuro-symbolic AI feedback loop. Neuro-symbolic AI combines machine learning’s flexibility with automated reasoning’s provable correctness. An LLM generates policies from natural language, while Cedar Analysis validates them using symbolic, mathematical reasoning. The following diagram illustrates this workflow:

Figure 1: Cedar policy generation workflow

Figure 1: Cedar policy generation workflow

An administrator specifies—in natural language—which MCP tools the agent can call and under what conditions. The neuro-symbolic feedback loop then formalizes this description into Cedar policies. Here’s how it works: first, the LLM translates the natural language into Cedar policies. These policies are then run through two stages of verification. In the first stage, AgentCore Policy uses a Cedar schema generator that takes the MCP tool descriptions and produces a Cedar schema. Cedar validates the policies against this schema, helping to ensure that they reference valid tools and parameters and ruling out whole classes of runtime errors. If validation passes, the second stage runs Cedar Analysis, which encodes each policy as a mathematical formula and detects issues like policies that grant or deny everything, or that contain impossible conditions. These mathematical proofs identify errors in the process of translating from the natural language description to Cedar policies, and guide corrections.

The neuro-symbolic feedback loop significantly improves the accuracy of the generated policies. This demonstrates the power of combining neural and symbolic approaches—the LLM provides creative translation from natural language, while automated reasoning provides rigorous validation.

Control plane: When attaching policies to an AgentCore Gateway, Cedar Analysis performs holistic analysis of the entire policy set. Instead of analyzing policies in isolation, it examines how they interact and their combined effect. This analysis identifies potential logical errors—such as conflicting or redundant policies—and detects whether the policy set produces unintended authorization outcomes. When Cedar Analysis detects these errors, the operation fails and returns a description of the issue, so the policy author can fix and retry. See the Formal analysis for policy verification section for examples of the checks.

MCP tool invocation enforcement: Each agent tool request made to the AgentCore gateway is evaluated against Cedar policies which determine whether the MCP tool invocation with the given arguments should be allowed. This creates the safety envelope while allowing the necessary bridges to enable the agent to perform its job.

MCP tool filtering: Cedar enables an additional layer of protection that operates before any tool invocation occurs. When an agent issues a list tools command, AgentCore Gateway uses Cedar’s partial evaluation capability to determine which actions would always be denied under the current policy set. Those actions are omitted from the list tool response. The agent and the underlying LLM never see those tool actions, eliminating an entire class of risk: the agent and LLM can’t attempt to invoke a tool it doesn’t know exists. This is a direct benefit of Cedar’s partial evaluation: the system can determine that certain tool actions are unreachable without needing to wait for an actual tool invocation attempt.

Why Cedar: Analyzability enables safety at scale

Natural language is too ambiguous for security-critical infrastructure, and general-purpose programming languages, like Python, are very expressive but too difficult to analyze. They can have unintended side effects, termination issues, and can be difficult to understand.

Cedar avoids these issues by excluding loops and stateful operations, so policy evaluation terminates in O(n) time in common cases. This bounded execution time means agents can make authorization decisions without disrupting user experience or workflow efficiency.

Cedar is straightforward to read. Regulatory compliance and security audits require policies that humans can understand and verify. Cedar policies read like structured natural language, making them accessible to security teams, compliance officers, and business stakeholders:

// Only allow bulk discounts for premium customers with sufficient quantity
permit (
  principal is AgentCore::OAuthUser,
  action == AgentCore::Action::"ApplyBulkDiscount",
  resource
)
when
{
  principal.hasTag("customer_tier") &&
  principal.getTag("customer_tier") == "Platinum" &&
  context.input.orderQuantity >= 50
}
unless
{
  context.input
    .productTypes
    .containsAny
    (
      ["limited_edition", "seasonal_specials"]
    )
};

Auditors without a technical background can understand this policy: “Allow bulk discounts for platinum customers who order at least 50 items, except for limited edition or seasonal special products.” The unless clause makes the exception clear, which is how business rules are typically expressed in natural language. Notice that this single policy constrains two different sources of data. The customer tier comes from a JSON Web Token (JWT) claim—it can’t be hallucinated or manipulated by the LLM. The tool inputs like order quantity and product types, however, originate from the LLM’s tool call. Cedar policies constrain these inputs to only allowed values, ensuring that even if the LLM produces unexpected arguments, the policy enforcement layer rejects them deterministically.

Cedar is the right choice because it’s fast, straightforward to read, and analyzable through automated reasoning. This analyzability is why you can reason about the safety envelope around agents that’s expressed as Cedar policies. As agentic systems grow the number of tools grows. Without proper tooling, policy management becomes intractable; policies can conflict, create security gaps, or produce unintended authorization outcomes.

In the rest of this section, we examine how Cedar’s analyzability directly addresses this challenge through its deterministic, mathematically sound analysis. Because Cedar analysis can reliably detect conflicts and logical errors across large policy sets it enables scalable policy management through neuro-symbolic AI.

Formal analysis for policy verification

Cedar policies can be encoded as mathematical formulas and analyzed using automated reasoning techniques through a symbolic encoder. This enables AgentCore Policy to provide sophisticated policy verification capabilities during policy authoring and beyond. AgentCore Policy uses this analysis when authoring or attaching policies to detect possible logical errors, such as conflicting or redundant policies. Policy analysis, including policy comparison is available as an open source CLI tool. Next, we will take a look at some concrete examples of these checks.

Detecting logical errors in policies: Cedar Analysis can detect when policies contain logical errors. For example, the following policy has contradictory constraints that mean it can’t allow any request: the customer tier can’t be both gold and platinum at the same time. The intention was to use an || instead of &&, a mistake that can be made by both humans and AI systems that author policies.

// This policy cannot allow any requests due to logical errors
permit (
  principal is AgentCore::OAuthUser,
  action == AgentCore::Action::"ProcessRefund",
  resource
)
when
{
  principal.hasTag("customer_tier") &&
  principal.getTag("customer_tier") == "Gold" &&
  principal.getTag("customer_tier") == "Platinum"
}
unless { context.input.refundAmount > 1000 };

Similarly, Cedar Analysis can detect policies that always allow a given action, usually an indication of an overly permissive policy. For example, the following policy will allow all ApplyBulkDiscount requests because any order quantity will either be greater than or equal to 100 or less than 100.

// This policy allows all ApplyBulkDiscount requests
permit (
  principal is AgentCore::OAuthUser,
  action == AgentCore::Action::"ApplyBulkDiscount",
  resource
)
when
{
  context.input.orderQuantity >= 100 ||
  context.input.orderQuantity < 100 ||
  (principal.hasTag("customer_tier") &&
   principal.getTag("customer_tier") == "Platinum")
};

Detecting such logical errors isn’t easy for humans, and can’t be done by pattern matching: you need the formal rigor of mathematical analysis, which is exactly what Cedar Analysis does.

Detecting policy conflicts: Cedar Analysis can also analyze the entire policy set to detect inconsistencies between different individual policies:

// These policies conflict - Analysis will detect the subtle issue
permit (
  principal is AgentCore::OAuthUser,
  action == AgentCore::Action::"ProcessRefund",
  resource
)
when
{
  principal.hasTag("customer_tier") &&
  principal.getTag("customer_tier") == "Gold" &&
  context.input.refundAmount < 100
};

forbid (
  principal is AgentCore::OAuthUser,
  action == AgentCore::Action::"ProcessRefund",
  resource
)
when
{
  principal.hasTag("customer_tier") &&
  ["Gold", "Platinum"].contains(principal.getTag("customer_tier")) &&
  context.input.refundAmount < 500
};

The permit policy allows gold customers to process refunds less than $100, while the forbid policy blocks gold customers (and platinum customers) from processing refunds less than $500. Because forbid overrides permit in Cedar, the forbid policy would block all gold customer refunds despite the permit policy.

Comparing policy changes: When updating policies, Cedar Analysis can also determine the exact impact of a change. Consider the following update to the unless clause (the policy lines with + have been added and those with - have been removed): we now block ApplyBulkDiscount only when the product type is limited_edition and the quantity exceeds 200.

 permit (
   principal is AgentCore::OAuthUser,
   action == AgentCore::Action::"ProcessRefund",
   resource
 )
 when
 {
   context.input.refundAmount < 500
 };
 
 permit (
   principal is AgentCore::OAuthUser,
   action == AgentCore::Action::"ApplyBulkDiscount",
   resource
 )
 when
 {
   context.input.orderQuantity >= 50
 }
 unless
 {
-  context.input.productTypes.containsAny(["limited_edition"])
+  context.input.productTypes.containsAny(["limited_edition"]) &&
+  context.input.orderQuantity > 200
 };

At first glance, adding a condition to the unless clause might seem more restrictive. In fact, it’s the opposite: narrowing when the unless applies means the permit now covers more requests. For example, an order of 73 units of a limited_edition product would have been blocked before but is now allowed. Cedar Analysis can automatically detect this and generates the following table showing the difference in permissiveness between the original policy set and the updated one:

Principal type

Action

Resource type

Status

OAuthUser

ProcessRefund

Gateway

Equivalent

OAuthUser

ApplyBulkDiscount

Gateway

More permissive

In the preceding example, the analysis tells us that the updated policy allows allows exactly the same ProcessRefund requests, but allows more ApplyBulkDiscount requests.

This formal verification capability is essential when agents operate autonomously and can affect the real world. Organizations need mathematical certainty that their policies will behave as intended.

Deterministic behavior for reliable governance

Unlike probabilistic AI models, enterprise security requires deterministic guarantees. Cedar policies always produce the same authorization decision for identical requests, regardless of evaluation order or system state. Cedar’s default deny, forbid wins, no ordering semantics help ensure predictable behavior.

// Policy evaluation order does not affect the authorization decision
permit(
    principal,
    action == AgentCore::Action::"ProcessRefund",
    resource
) when {
    context.input.refundAmount < 500
};

forbid(
    principal,
    action == AgentCore::Action::"ProcessRefund", 
    resource
) when {
    context.input.orderDate.offset(duration("90d")) < context.system.now
};

Whether the permit or forbid policy is evaluated first, a refund request over $500 will always be denied, and any refund issued more than 90 days after the order date will also be denied. This predictability gives enterprises confidence in their agent governance.

From policies to production

By choosing AgentCore Policy and Cedar, organizations can deploy autonomous agents with policies they can reason about mathematically, not only hope the agents work correctly. Cedar’s combination of expressiveness, readability, and formal verification means that you can design agents with the flexibility needed to function and the certainty security teams demand.

Automated reasoning has already proven its value across AWS, from AWS IAM Access Analyzer verifying access policies to provable security for network configurations. Applying these same techniques to agentic AI is a natural extension: as agents take on more responsibility, the need for mathematically grounded guarantees only grows. The neuro-symbolic approach we’ve described in this post—combining LLM flexibility with the rigor of automated reasoning—points toward a future where agents can be both more autonomous and more trustworthy, because the verification keeps pace with the autonomy.

Learn more

Policy is now available as part of Amazon Bedrock AgentCore Gateway. To learn more about Cedar and its capabilities, visit the Cedar website, try the Cedar playground, or join the Cedar community on Slack.

For more information about Policy in Amazon Bedrock AgentCore Gateway, visit the AWS documentation or explore the AgentCore Gateway console.

If you have feedback about this post, submit comments in the Comments section below.

Liana Hadarean

Liana Hadarean

Liana is a Principal Applied Scientist at AWS. She has worked on the code analysis tools that power Amazon Q Java security detectors, and is now a contributor to the Cedar policy language.

John Tristan

Jean-Baptiste Tristan

Jean-Baptiste is a Senior Principal Applied Scientist at AWS Agentic AI where he works on neurosymbolic AI and agentic safety.

Automate root cause analysis across Datadog and Elasticsearch with AWS DevOps Agent

Post Syndicated from Bhuvan Jain original https://aws.amazon.com/blogs/devops/automate-root-cause-analysis-across-datadog-and-elasticsearch-with-aws-devops-agent/

Modern distributed systems route business transactions through dozens of microservices, message queues, and event streams. When a message fails to process or processing exceeds SLA thresholds, troubleshooting requires correlating logs from tools like Elasticsearch, metrics from Datadog, and infrastructure change events in AWS CloudTrail. Correlating these signals manually across heterogeneous backends, each with different query languages, schemas, and time granularities, can take hours per incident and demands deep institutional knowledge of the system topology.

This post shows how AWS DevOps Agent, combined with a custom Model Context Protocol (MCP) server for Elasticsearch and native Datadog integration, automates end-to-end root cause analysis. When a Datadog alert fires, AWS DevOps Agent automatically initiates an investigation, correlates signals across all observability backends, and delivers root cause findings in minutes, without manual intervention.

In this post, we walk through the architecture, configuration steps, and a real-world scenario demonstrating how AWS DevOps Agent dramatically reduces mean time to identify (MTTI) for distributed system failures. DevOps engineers, site reliability engineers (SREs), and operations leaders managing containerized workloads will learn how to implement alert-triggered automated investigations that eliminate manual correlation and accelerate root cause identification in their own environments.

Challenges in correlating telemetry signals at scale

At scale, correlating telemetry signals across distributed systems is a key challenge. A platform processing billions of communications for regulated industries must track every message through its full lifecycle — ingestion, transformation, policy evaluation, archival, and retrieval — across dozens of production clusters, thousands of worker nodes, and terabytes of daily telemetry spread across multiple observability backends. A single message ID can generate log entries across multiple indices, correlated metrics in monitoring systems, and change events in audit trails. When a message goes missing or processing stalls, the operations team must pinpoint which cluster processed it, which log store holds the evidence, whether a recent deployment preceded the failure, and whether the issue is isolated or systemic — all while context-switching across tools with different query languages and data schemas. Before AWS DevOps Agent, this process routinely took hours per incident, and longer for complex multi-service failures.

The core difficulty is not the volume of data. It is the correlation of signals across heterogeneous systems that use different identifiers, different time granularities, and different data schemas. A message ID in Elasticsearch logs must be correlated to:

  • A trace ID in application performance monitoring (APM) systems
  • A pod name and namespace in Kubernetes event logs
  • A container image tag in Amazon Elastic Container Registry (ECR) push events
  • Metric anomalies (error rate spikes, pod restarts, CPU/memory deviations) in Datadog
  • Deployment events captured in AWS CloudTrail logs

Manual correlation requires engineers to maintain mental models of these relationships while executing queries across multiple systems. It is error-prone, non-repeatable, and heavily dependent on institutional knowledge. When the engineer with the deepest system familiarity is unavailable, resolution times increases.

Prerequisites

Complete the following prerequisites before configuring the integrations:

  1. The AWS Command Line Interface (AWS CLI) version 2. For installation instructions, see installing or updating to the latest version of the AWS CLI.
  2. Helm – the Kubernetes package manager used to deploy the sample application.
  3. Kubectl – the Kubernetes command-line tool used to deploy Filebeat and manage cluster resources.
  4. An EKS cluster with Control plane logs enabled.
  5. AWS DevOps Agent Agentspace. For installation instructions, refer to Creating an Agent Space.
  6. Elasticsearch cluster deployed and accessible (EC2-hosted, Amazon OpenSearch Service, or self-managed). Filebeat configured as a DaemonSet to collect pod logs and forward to Elasticsearch.
  7. Datadog account with API key and application key. To create, see API & Applications key.

Solution Architecture

The solution presented in this post combines three integrated components to deliver automated end-to-end message ID traceability:

  • AWS DevOps Agent as the intelligent investigation orchestrator
  • A custom ELK MCP Server providing structured access to Elasticsearch log data
  • Native Datadog integration for metrics, events, and alert-triggered investigations

Together, these components form an autonomous investigation pipeline that activates when an alert fires, correlates signals across all observability sources, builds a topological understanding of the affected services, and delivers a structured root cause analysis, without manual intervention.

In our implementation, application pods are instrumented to emit custom metrics to Datadog, including per-message-ID processing status, trace ID labels, and endpoint-level error counters. This instrumentation provides AWS DevOps Agent with the ability to correlate a specific message ID from an alert payload to its corresponding trace ID in application performance data, a correlation that previously required manual cross-referencing.

Webhook-Based Alert Triggering

A critical aspect of the architecture is the automated triggering of investigations when alerts fire. Rather than requiring manual investigation initiation, the solution configures Datadog alerting webhooks to invoke AWS DevOps Agent directly.

When a Datadog monitor enters an alert state, it fires a webhook to the AWS DevOps Agent endpoint, including:

  • The message ID associated with the processing failure
  • The trace ID for APM correlation
  • The alert timestamp and alert condition
  • The triggering monitor name and severity

AWS DevOps Agent authenticates the webhook using a bearer token and immediately initiates an investigation in the configured Agent Space. The Datadog webhook payload serves as the investigation’s initial context, seeding the agent with the specific identifiers it needs to perform targeted queries rather than broad searches across the full data volume.

Architecture Diagram

Architecture diagram showing the automated root cause analysis pipeline. A Datadog alert fires a webhook to AWS DevOps Agent, which queries three sources: an ELK MCP Server connected to Elasticsearch for log data, native Datadog integration for metrics, and AWS CloudTrail for deployment events. Results flow back to the Agent Space for correlated root cause analysis.
Figure 1:
Automated root cause analysis pipeline — from Datadog alert to AWS DevOps Agent investigation across Elasticsearch, Datadog, and AWS CloudTrail

Implementation Walkthrough

The following walkthrough describes the end-to-end setup required to replicate the message ID traceability solution in your own environment.

Step 1: Configure EKS Cluster Access for AWS DevOps Agent

AWS DevOps Agent requires an access entry in each EKS cluster it will investigate. This enables the agent to describe Kubernetes objects, retrieve pod logs, and access cluster events.

  1. In the AWS DevOps Agent console, navigate to your Agent Space and select the Capabilities tab.
  2. Under the Cloud section, select the primary source and choose Edit. Note the Role Name shown in the Role Name field, this is the IAM role that requires EKS access.
  3. In the Amazon EKS console, select each cluster and open the Access tab.
  4. Under IAM Access Entries, choose Create to add a new access entry.
  5. Set the IAM Principal ARN to the Agent Space role noted in step 2.
  6. Under Access Policies, select AmazonAIOpsAssistantPolicy with Cluster scope. Choose Add Policy, then Next.
  7. Review and create the access entry.

At scale: For environments with 50+ clusters, use the AWS CLI, Terraform, or a GitOps pipeline to automate access entry creation across all clusters. The following CLI command creates an access entry for a single cluster:

aws eks create-access-entry --cluster-name <CLUSTER_NAME> --principal-arn <AGENTSPACE_ROLE_ARN> --region <REGION>
aws eks associate-access-policy --cluster-name <CLUSTER_NAME> --principal-arn <AGENTSPACE_ROLE_ARN> --policy-arn arn:aws:eks::aws:cluster-access-policy/AmazonAIOpsAssistantPolicy --access-scope type=cluster --region <REGION>

Step 2: Configure Datadog Integration in AWS DevOps Agent

AWS DevOps Agent includes native Datadog integration. Configuration requires your Datadog API credentials and designates the integration as a data source in the Agent Space. In the AWS DevOps Agent console, navigate to Integrations and choose Add Integration and follow the steps.

After configuration, AWS DevOps Agent can query Datadog metrics, monitors, and events during investigations. Custom application metrics (message throughput, error rates, processing status per message ID) are automatically accessible once the integration is active.

Step 3: Deploy and Configure the Custom ELK MCP Server

The Elasticsearch MCP server bridges AWS DevOps Agent to your self-managed Elasticsearch deployment. The MCP server is deployed as a publicly accessible endpoint with TLS authentication, enabling AWS DevOps Agent to call Elasticsearch APIs securely without requiring direct network access to the actual Elasticsearch/Kibana instances.

Note: For basic Elasticsearch integration, the official Elasticsearch MCP server provides a ready-to-use option. For this use case, we built a custom Python MCP server using FastMCP to expose investigation-specific tools — trace ID correlation, time-window log retrieval, and latency analysis — tailored to our message traceability workflow.

The custom server implementation provides the thirteen tools required for log search, index discovery, and aggregation.

Table: ELK MCP Server tools access by AWS DevOps Agent during investigations
MCP Tool Description
search_logs Search by Lucene query string, time range, and log level
get_error_summary Top recurring errors within a time window
get_recent_logs Fetch most recent log entries from an index
get_logs_by_service Filter logs by service or application name
count_logs_by_level Breakdown of log counts by level (ERROR, WARN, INFO, DEBUG)
get_slow_requests Find requests exceeding a latency threshold
get_logs_around_time Fetch logs within ±N minutes of a specific timestamp
search_by_trace_id Find all logs for a specific trace, request, or correlation ID
get_unique_errors Get distinct error messages in a time window
list_indices List all available Elasticsearch indices with doc counts and health
get_index_stats Get size, document count, and health of a specific index
get_logs_by_host Filter logs by the hostname that sent them via Filebeat
get_logs_by_file Filter logs by the source log file path
  1. Launch an Ubuntu instance (t4g.medium or larger) with a security group allowing inbound TCP 443 from AWS DevOps Agent service endpoints.Note: The single-instance deployment described here is intended for demonstration purposes and does not provide high availability. For production workloads requiring managed infrastructure, automatic scaling, and built-in resilience for your MCP servers, consider using Amazon Bedrock AgentCore Runtime.
  2. Install dependencies and obtain a TLS certificate:
    sudo apt update &&sudo apt install -y python3 python3-venv certbot
    python3 -m venv ~/elk-mcp-venv
    source ~/elk-mcp-venv/bin/activate
    pip install mcp elasticsearch uvicorn starlette
    sudo certbot certonly --standalone -d elk-mcp.yourcompany.com
  3. Create the MCP server. The key architectural decisions are: FastMCP for the Streamable HTTP transport, Starlette middleware for API key authentication, and environment variables for configuration:
    import json, os
    from mcp.server.fastmcp import FastMCP
    from elasticsearch import Elasticsearch
    from starlette.middleware.base import BaseHTTPMiddleware
    from starlette.responses import JSONResponse
    
    ES_HOST = os.environ.get("ES_HOST", "http://localhost:9200")
    API_KEY = os.environ.get("MCP_API_KEY", "YOUR_API_KEY")
    es = Elasticsearch(hosts=[ES_HOST])
    mcp = FastMCP("elk-logs", host="elk-mcp.yourcompany.com")
    
    # API key authentication middleware
    class APIKeyMiddleware(BaseHTTPMiddleware):
        async def dispatch(self, request, call_next):
            if request.headers.get("x-api-key") != API_KEY:
                return JSONResponse({"error": "Unauthorized"}, status_code=401)
            return await call_next(request)
    
    # Example: trace ID correlation tool
    @mcp.tool
    def search_by_trace_id(trace_id: str, index: str, size: int = 100) -> str:
        """Find all logs for a specific request or trace ID."""
        result = es.search(index=index, body={
            "query": {"multi_match": {
                "query": trace_id,
                "fields": ["trace_id", "request_id", "correlation_id", "traceId"]
            }},
            "sort": [{"@timestamp": "asc"}],
            "size": size
        })
        return json.dumps([h["_source"] for h in result["hits"]["hits"]], indent=2)
    
    # ... additional tools follow the same pattern
    
    app = mcp.streamable_http_app()
    app.add_middleware(APIKeyMiddleware)
    
    if __name__ == "__main__":
        import uvicorn
        uvicorn.run(app, host="0.0.0.0", port=443,
            ssl_keyfile="/etc/letsencrypt/live/elk-mcp.yourcompany.com/privkey.pem",
            ssl_certfile="/etc/letsencrypt/live/elk-mcp.yourcompany.com/fullchain.pem")
  4. Start the server:
    sudo -E ES_HOST=http://<ELASTICSEARCH_IP>:9200 MCP_API_KEY=<YOUR_API_KEY> nohup ~/elk-mcp-venv/bin/python ~/elk_mcp_server.py > ~/mcp.log 2>&1 &
  5. Register in AWS DevOps Agent:
    1. In the AWS DevOps Agent console, navigate to Integrations -> Add MCP Integration.
    2. Enter the endpoint URL: https://elk-mcp.yourcompany.com:443/mcp
    3. Enter the API key for authentication.
    4. Verify the integration shows all available tools in the integration detail view.
    5. Add the MCP integration to your Agent Space under the Integrations tab.

Note: The MCP server must be publicly accessible over HTTPS. If your Elasticsearch cluster is in a private VPC, deploy the MCP server with network access to the cluster (e.g., in the same VPC or a peered VPC) while exposing only the MCP server endpoint publicly. Use security group rules to restrict access to AWS DevOps Agent’s known egress IP ranges where possible.

Step 4: Deploy the Application and Configure Filebeat on EKS

Filebeat runs as a Kubernetes DaemonSet on each EKS cluster, collecting pod logs and enriching them with Kubernetes metadata before forwarding to Elasticsearch. The following pipeline configuration ensures that message IDs and trace IDs are preserved as indexed fields, enabling efficient targeted queries during investigations.

  1. Clone the Repository and Build the Container Image:
    # Clone the DevOps agent sample repository
    git clone https://github.com/aws-samples/Amazon-prometheus-bedrock-agent-example.git
    
    # Navigate to the smart demo directory
    cd devops-agent/smart-demo-main/
    
    # Authenticate Docker to your ECR registry
    aws ecr get-login-password --region us-west-2 | docker login --username AWS --password-stdin <your-account-id>.dkr.ecr.us-west-2.amazonaws.com
    
    # Build the container image
    docker build -t sample-app .
    
    # Tag the image for ECR
    docker tag sample-app:latest <your-account-id>.dkr.ecr.us-west-2.amazonaws.com/smart-demp:latest
    
    # Push the image to ECR
    docker push <your-account-id>.dkr.ecr.us-west-2.amazonaws.com/smart-demp:latest
  2. Deploy the Application to EKS:
    # Deploy the sample application to EKS using Helm
    helm install sample-app ./helm --set image.repository=<your-account-id>.dkr.ecr.us-west-2.amazonaws.com/smart-demp --set image.tag=latest
  3. Deploy Filebeat as DaemonSet:
    # Navigate to the Filebeat directory
    cd filebeat
    
    # Apply the Filebeat ConfigMap (autodiscovery, JSON parsing, K8s metadata enrichment, Logstash output)
    kubectl apply -f filebeat-configmap.yaml
    
    # Deploy Filebeat as a DaemonSet on every node in the cluster
    kubectl apply -f filebeat-ds.yaml

Step 5: Configure Datadog Webhook for Automatic Investigation Triggering

We will automatically trigger AWS DevOps Agent investigations when Datadog alerts fire. This eliminates the human latency between alert detection and investigation initiation.

Retrieve the AWS DevOps Agent webhook URL and secret:

  1. In the AWS DevOps Agent console, navigate to your Agent Space and open the Capabilities tab.
  2. Under the Webhook section, choose Configure, then Generate webhook.
  3. Save the webhook URL and HMAC secret. These credentials are used to authenticate webhook requests from Datadog.

In Datadog, configure a webhook integration:

  1. Navigate to Integrations -> Webhooks and create a new webhook.
  2. Set the URL to the AWS DevOps Agent webhook endpoint.
  3. Add the Authorization header with the bearer token from step 3.
  4. Configure the payload to include the message ID, trace ID, and alert context:
    {
    "title": "Message Processing Failure - $EVENT_TITLE",
    "description": "$EVENT_MSG",
    "alert_id": "$ALERT_ID",
    "alert_status": "$ALERT_STATUS",
    "timestamp": "$TIMESTAMP",
    "message_id": "$tags.message_id",
    "trace_id": "$tags.trace_id",
    "service": "$tags.service",
    "cluster": "$tags.cluster_name",
    "severity": "$ALERT_PRIORITY"
    }
  5. Associate the webhook with the Datadog monitors that detect message processing failures by adding @webhook-webhook-name to the monitor notification message.

Step 6: Configure Agent Space Skills (Optional but Recommended)

AWS DevOps Agent Skills provide a Retrieval-Augmented Generation (RAG) knowledge base that gives the agent organization-specific context during investigations. Even a brief skills document (2-3 paragraphs) that identifies your application’s purpose, its key components, and its observability backends can reduce AWS DevOps Agent investigation time by helping the agent understand context before executing its first queries.

In our implementation, the skills document described the sample message-processing application, identified Elasticsearch as the logging backend, and identified Datadog as the metrics backend.

Real-World Investigation: Message Processing Failure Diagnosed in 6 Minutes

The following walkthrough and the scenario represent a common class of incident in distributed systems: a silent functional regression introduced through a new container image deployment that causes specific message types to fail processing without immediately obvious symptoms.

The Scenario

The production EKS cluster runs a message-processing application (sample-app) with four HTTP endpoints:

  • /health – Application health check
  • /metrics – Prometheus metrics endpoint
  • /process – Core message processing endpoint
  • /alert – Alert notification endpoint (newly introduced in recent deployment)

A new container image was pushed to Amazon ECR with a new /alert endpoint. However, the endpoint implementation was incomplete when called; it returned an HTTP 404 response and silently dropped the associated message. The Filebeat DaemonSet collected pod logs and sent them into Elasticsearch. Datadog captured application metrics with message ID and trace ID labels. A Datadog monitor detected the elevated error rate and fired.

Phase 1: Alert Fires and Investigation Initiates (T+0:00)

At 14:52:57 UTC, a Datadog monitor detected an elevated rate of failed message processing requests on the /alert endpoint. The monitor fired a webhook to the AWS DevOps Agent endpoint with the alert payload context.

Within 10 seconds, the Agent read its investigation skills (sample-app-incident and triaging-3p-monitoring-alerts) and began planning the investigation approach.

Screenshot of AWS DevOps Agent console showing an investigation automatically initiated via Datadog webhook. The alert payload context includes message ID, trace ID, and alert timestamp. Investigation skills sample-app-incident and triaging-3p-monitoring-alerts are loaded
Figure 2: AWS DevOps Agent investigation initiated automatically via Datadog webhook, showing alert payload context and investigation skills loaded

Phase 2: Cross-Source Signal Correlation (T+0:10 – T+2:30)

AWS DevOps Agent began its investigation by using the message ID from the alert payload as its primary search key. It decided its investigation strategy: extract the trace_id from Elasticsearch using the message_id, get Datadog monitor details, and search for errors around the alert time.

Elasticsearch Log Search
The agent invoked the ELK MCP server to list available indices and identify the relevant log store for the message-processor application. It then executed a targeted search and identified the relevant Elasticsearch index (logs-2026.03.25):

Screenshot of AWS DevOps Agent querying the ELK MCP Server to correlate a message ID to a trace ID across Elasticsearch indices. The agent identifies the relevant log index logs and retrieves matching log entries
Figure 3: AWS DevOps Agent querying the ELK MCP Server to correlate message ID to trace ID across Elasticsearch indices

AWS DevOps Agent surfaced the Message ID to Trace ID correlation without any explicit cross-referencing instruction. It recognized the relationship from the log structure. At T+1:41, the DevOps Agent launched three parallel tasks simultaneously, rather than investigating sequentially.

Screenshot showing the trace ID successfully resolved from the Elasticsearch log structure, triggering three parallel investigation tasks: Datadog metrics correlation, EKS topology analysis, and CloudTrail event correlation.Figure 4: Trace ID successfully resolved from log structure, triggering three parallel investigation tasks

Datadog Metrics Correlation
Using the trace ID extracted from the Elasticsearch logs, the agent queried Datadog for correlated metrics. It retrieved CPU and memory utilization, pod count, restart metrics and enhanced metrics for request latency and errors.

Screenshot of Datadog metrics retrieved by AWS DevOps Agent using the extracted trace ID, showing CPU utilization, memory usage, pod restart counts, and request latency metrics for the affected service.
Figure 5: Datadog metrics correlation showing CPU, memory, pod restarts, and request latency retrieved using the extracted trace ID

AWS EKS Topology & CloudTrail Event Correlation
AWS DevOps Agent queried AWS CloudTrail for deployment and configuration change events in the time window preceding the alert.

Screenshot of AWS CloudTrail event correlation identifying deployment and configuration change events in the time window preceding the alert, including ECR image push and EKS rolling deployment events
Figure 6: AWS CloudTrail event correlation identifying deployment and configuration changes in the alert time window

With the initial timeline established, AWS DevOps Agent examined all endpoints and their response patterns. This revealed that the application was fundamentally healthy, with three of four endpoints returned consistent 200 responses. However, it also revealed the anomaly was isolated to the /alert endpoint, which had never successfully served a request in its observable history.

Screenshot of AWS DevOps Agent endpoint analysis showing three healthy endpoints returning HTTP 200 responses (health, metrics, process) and the alert endpoint returning consistent HTTP 404 failures, isolating the anomaly to the newly deployed alert endpoint.
Figure 7: AWS DevOps Agent endpoint analysis revealing isolated 404 failures on the /alert endpoint while other endpoints remain healthy

Phase 3: Observation Streaming from Parallel Tasks (T+2:30 – T+3:54)

As the three tasks ran simultaneously, observations streamed in chronologically:

T+2:58 – Observation: Anomalous CPU Behavior Signals Pod Disruption

The first sign of trouble came from pod tr8pl. Its CPU usage dropped sharply. Around the same time, two unfamiliar pods (85bx4, 7h4bd) briefly appeared with minimal CPU. Shortly after, three new pods (hclf9, b7bp2, g6gkc) spun up. This pattern of old pods dying, short-lived intermediaries, and fresh containers starting up pointed strongly toward a rolling deployment in progress.

T+3:04 – Observation: ECR Image Push Traced as the Trigger

With the deployment pattern established, the next question was: what initiated it? CloudTrail provided the answer. At 14:57:19 UTC, a user vik**** (via role nht-admin) pushed a new container image to ECR repository sm***demp:latest (ECR image tag). The timeline now made sense:

  1. ECR image push at 14:57:19 UTC
  2. Rolling deployment (pods replaced)
  3. /alert endpoint 404 errors begin
  4. Datadog alert fires

Screenshot showing parallel task observations streaming into AWS DevOps Agent. Anomalous CPU behavior indicates pod disruption from a rolling deployment, and CloudTrail evidence links an ECR image push by user vik at 14:57:19 UTC to the deployment that introduced the failing endpoint.
Figure 8: Parallel task observations streaming into AWS DevOps Agent – anomalous CPU behavior indicating pod disruption and CloudTrail evidence linking the ECR image push to the rolling deployment

Phase 4: Findings Documented – Causal Chain Established (T+3:55 – T+5:08)

At T+3:55, the Agent documented its first formal Finding (elevated from Observation):

Screenshot of AWS DevOps Agent documenting its formal finding, establishing the causal chain: ECR image push triggered rolling deployment, new container image contained incomplete alert endpoint implementation, endpoint returns 404 and drops messages.
Figure 9: AWS DevOps Agent formal finding documenting the causal chain from ECR image push to alert endpoint failure

Phase 5: Root Cause Confirmation and Infrastructure Validation (T+5:10 – T+5:30)

AWS DevOps Agent validated infrastructure health. The complete absence of infrastructure issues, combined with the timeline evidence from CloudTrail and the historical 404 pattern on the /alert endpoint, allowed AWS DevOps Agent to deliver a high-confidence root cause identification.

At 14:58:12 UTC, exactly 5 minutes and 14 seconds (under 6 minutes) after the investigation began, AWS DevOps Agent delivered its root cause analysis:

Screenshot of the final root cause analysis delivered by AWS DevOps Agent at 14:58:12 UTC, 5 minutes and 14 seconds after investigation began. Root cause identified as an incomplete alert endpoint in the newly deployed container image that returns HTTP 404 and silently drops associated messages.
Figure 10: Final root cause analysis delivered by AWS DevOps Agent, identifying the incomplete alert endpoint in the newly deployed container image

Clean-up

Step 1: Delete the AWS DevOps Agent AgentSpace

  1. In the AWS DevOps Agent console, navigate to Agent Spaces.
  2. Select the Agent Space you created for this walkthrough.
  3. Remove all integrations (Datadog, ELK MCP Server) from the Agent Space by navigating to the Capabilities tab and choosing Remove for each.
  4. Choose Delete Agent Space from Actions dropdown and confirm the deletion.

Step 2: Terminate the Microservices and Delete the EKS Cluster

First, remove the application workloads and Filebeat DaemonSet deployed on the cluster:

# Uninstall the sample application Helm release
helm uninstall sample-app

# Delete the Filebeat DaemonSet and ConfigMap
kubectl delete -f filebeat/filebeat-ds.yaml
kubectl delete -f filebeat/filebeat-configmap.yaml

Once the workloads are removed, delete the EKS cluster.

Step 3: Terminate EC2 Instances

Terminate the EC2 instances hosting both the MCP server and the Elasticsearch cluster. You can do this from the AWS Management Console or the AWS CLI:

# Terminate the MCP server EC2 instance
aws ec2 terminate-instances --instance-ids <MCP_SERVER_INSTANCE_ID> --region <REGION>

# Terminate the Elasticsearch EC2 instances
aws ec2 terminate-instances --instance-ids <ELASTICSEARCH_INSTANCE_ID> --region <REGION>

Conclusion

Distributed systems have created a correlation problem that scales faster than the human capacity to solve it. As microservices architectures grow to span dozens of clusters, hundreds of services, and terabytes of daily telemetry, the manual investigation practices that worked at smaller scale become the primary obstacle in maintaining operational quality.

AWS DevOps Agent addresses this challenge at its root by automating the multi-source correlation that previously required experienced engineers working across multiple systems. The combination of native Datadog integration, custom ELK MCP server connectivity, and AWS CloudTrail access enables AWS DevOps Agent to build the complete picture of an incident: from the first metric anomaly, through the log evidence, to the deployment event that caused it. The scenario described in this post demonstrates that a message processing incident that previously consumed hours can be diagnosed to root cause in under six minutes automatically, without manual intervention, and with the full investigation documented for audit and learning purposes.

About the Authors

Bhuvan Jain

Bhuvan Jain

Bhuvan is a Senior Technical Account Manager at Amazon Web Services, supporting independent software vendor (ISV) customers. He is passionate about helping customers build Well-Architected solutions on AWS, with a focus on enterprise-scale networking. As a subject matter expert, Bhuvan offers guidance on designing network architectures that are highly available, resilient, and cost-effective. He holds a Master’s degree in Electrical and Computer Engineering from the University of Illinois at Chicago (UIC). In his free time, he enjoys playing basketball and volleyball, as well as watching movies and TV series.

Vikram Venkataraman

Vikram Venkataraman

Vikram Venkataraman is a Principal Specialist Solutions Architect at Amazon Web Services. He helps customers modernize, scale, and adopt best practices for containerized workloads on Amazon EKS. With the emergence of AI-powered automation, Vikram has been actively working with customers to leverage AWS AI/ML services to solve complex operational challenges, streamline monitoring workflows, and enhance incident response through intelligent automation. He designed and built the POC architecture described in this post and is a co-author of the EKS knowledge graphs blog.

Agentic application modernization at scale with Strands and Amazon Transform custom

Post Syndicated from Kanishk Mahajan original https://aws.amazon.com/blogs/devops/use-generative-ai-agents-for-application-modernization-at-scale-with-strands-amazon-transform-custom-and-amazon-bedrock-agentcore/

Introduction

Modernizing applications by upgrading language runtimes, migrating SDKs, and refactoring frameworks is important for cloud adoption but can be labor-intensive at scale. Each repository requires analysis of dependencies and transformation needs; custom transformation logic must be built and validated, and changes are often executed sequentially across codebases. If you have hundreds of applications, this stretches timelines from months to years, while introducing inconsistency across your teams.

To address this, Amazon Web Services (AWS) provides a composable set of building blocks. AWS Transform custom enables reusable, CLI-driven code transformations for upgrading runtimes, SDKs, and frameworks consistently across large portfolios. Strands Agents provides a framework for building multi-agent systems that coordinate complex transformation workflows. Amazon Bedrock AgentCore delivers the managed runtime, memory, and observability to operate these agents reliably in production. Together, they replace manual, sequential modernization with an intelligent, automated approach that scales.

In this post, we show you how to combine these services to build a generative AI–powered, agentic modernization system that can automatically analyze application repositories, determine required changes, create missing transformations, and execute them in parallel at scale.

Solution overview

The solution uses an agentic architecture that separates intelligent decision-making from deterministic execution, enabling automation at scale while maintaining consistency and control. In this post, you will build an AI-driven application modernization system that demonstrates how multi-agent workflows can be applied to large-scale code transformation scenarios. You interact with the system through a React-based frontend or API interface, submitting individual repositories or batch workloads via CSV inputs. Requests are processed asynchronously through an API layer that invokes an orchestrator agent running on Amazon Bedrock AgentCore, which coordinates specialized agents to analyze codebases, identify transformation requirements, and manage execution workflows. Results are stored and surfaced through the interface, allowing users to track progress and review outputs in real time.The workflow begins with repository analysis, where the system inspects application codebases to identify languages, dependencies, and required upgrades such as runtime version changes or SDK migrations. Based on this analysis, the system maps each application to an existing transformation when available. If no suitable transformation exists, a creation agent dynamically generates one using natural language instructions and publishes it to a centralized registry for reuse, creating a continuously improving system where transformation coverage expands over time.

Once transformations are identified or created, an execution agent runs them at scale by invoking AWS Batch jobs that execute the AWS Transform custom CLI, enabling parallel processing across multiple repositories. The orchestrator coordinates all agents, maintains workflow state using Amazon Bedrock AgentCore Memory, and ensures reliable execution through structured task decomposition, tool invocation, and error handling. While the example focuses on application re-platforming, the same architectural pattern can be applied to other large-scale code analysis and automation workflows.

The following architecture diagram (Figure 1) illustrates the various components of our solution as outlined in this section:architecture diagram describing the multi agent strands and agentcore deployment

Figure 1: AWS Transform custom Agentic Orchestration Architecture using Strands agents and Amazon Bedrock AgentCore

Prerequisites

Complete the following prerequisites:

  1. Install the AWS Command Line Interface (AWS CLI).
  2. Install the AWS SAM CLI v1.100.0+
  3. Install Docker v20.x+.
  4. Install Node.js v18.x+
  5. Install Python v3.11+
  6. Install the AWS CDK CLI
  7. Enable access to a Bedrock model for the orchestrator in your deployment region. The default model can be configured through the Amazon Bedrock model access console. To use a different model, set `BEDROCK_MODEL_ID` in `deployment/config.env` before Step 3 and enable access to that model instead. Model access approval can take a few minutes in some accounts, so complete this step before deploying.

Dependencies

The Strands Agents implementation has the following dependencies that are packaged in the DockerFile:

  1. Strands multi-agent framework: strands-agents
  2. Strands agent tools and utilities: strands-agents-tools
  3. HTTP library for API calls: requests
  4. Amazon Bedrock AgentCore SDK: bedrock-agentcore
  5. AWS SDK for Python: boto3

Deploy the solution

The solution is available for download on the GitHub repo. This post walks through the CDK + SAM deployment path (Option A in the repository README). The repository also includes a CDK-only option (Option B); see the repository README for details.

Step 1: Clone the repository

git clone https://github.com/aws-samples/aws-transform-custom-samples.git

cd aws-transform-custom-samples/agentic-atx-platform

Step 2: Configure AWS Credentials

# Configure AWS CLI

aws configure

# Verify credentials

aws sts get-caller-identity

Step 3: Deploy ATX CLI Container image and frontend using AWS CDK

# Copy configuration template (defaults work for most setups; edit only to change region or Bedrock model)

cd deployment

cp config.env.template config.env

# Authenticate with Amazon ECR Public (required for the Docker base image pull)

aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws

# Build the UI placeholder so CDK’s UI stack has ui/dist/ to deploy

cd ../ui && npm install && npx vite build

# Install CDK dependencies and bootstrap (run once per account/region)

cd ../cdk

npm install cdk bootstrap

# Build TypeScript and deploy the three stacks

npx tsc

CDK_DEFAULT_ACCOUNT=$(aws sts get-caller-identity --query Account --output text)

cdk deploy AtxContainerStack AtxInfrastructureStack AtxUiStack --require-approval never

# Note for accounts without a default VPC , pass the VPC context flags to `cdk deploy`:

cdk deploy AtxContainerStack AtxInfrastructureStack AtxUiStack --require-approval never

cdk deploy AtxContainerStack AtxInfrastructureStack AtxUiStack --require-approval never -c existingVpcId=vpc-xxx -c existingSubnetIds=subnet-aaa,subnet-bbb -c existingSecurityGroupId=sg-ccc

# Subnets must be public (auto-assign public IP enabled) or private with a NAT gateway so Fargate tasks can reach Amazon ECR, Amazon S3, and Git repositories.

Step 4: Deploy Strands Agents to AgentCore runtime using AWS SAM

cd ../sam./deploy.sh

# Invoke the deploy Lambda to create the AgentCore Runtime via the bedrock-agentcore-control SDK (takes 2-5 minutes)

aws lambda invoke --function-name atx-deploy-agentcore \ --region us-east-1 \ --cli-binary-format raw-in-base64-out \ --payload '{"action":"deploy"}' \ --cli-read-timeout 900 /tmp/deploy-output.jsoncat /tmp/deploy-output.json

Step 5: Wire the AgentCore runtime ARN into the async invoke Lambda

ACCOUNT_ID=$(aws sts get-caller-identity --query Account --output text)

RUNTIME_ARN=$(python3 -c "import json; print(json.loads(json.load(open('/tmp/deploy-output.json'))['body'])['runtime_arn'])")aws lambda update-function-configuration \ --function-name atx-async-invoke-agent \ --region us-east-1 \ --environment "Variables={AGENT_RUNTIME_ARN=${RUNTIME_ARN},RESULT_BUCKET=atx-custom-output-${ACCOUNT_ID},JOBS_TABLE=atx-transform-jobs}"

Step 6: Rebuild and deploy the frontend with AgentCore API endpoint

# Update the React application with the deployed API endpoint and redeploy it.

API_URL=$(aws cloudformation describe-stacks \ --stack-name AtxAgentCoreSAM \ --region us-east-1 \ --query 'Stacks[0].Outputs[?OutputKey==`ApiEndpoint`].OutputValue' \ --output text)

cd ../ui

VITE_API_ENDPOINT=$API_URL npx vite build./deploy-aws.sh

# This rebuilds the React application with the correct API endpoint, uploads it to Amazon S3, and invalidates the Amazon CloudFront distribution.

Step 7: Access the application

# After deployment completes, retrieve the CloudFront distribution URL from the AWS CloudFormation outputs and open it in your browser to access the application UI.

aws cloudformation describe-stacks \ --stack-name AtxUiStack \ --region us-east-1 \ --query 'Stacks[0].Outputs[?OutputKey==`WebsiteUrl`].OutputValue' \ --output text

Using the application

The UI exposes five tabs covering the complete modernization workflow: browsing available transformations, executing a transformation on a single repository, creating a new custom transformation with natural language, batch-processing a CSV of repositories, and tracking job status. This section walks through two of the most common flows.

Create a custom transformation from natural language

Open the Create Custom tab, describe the transformation in plain English (for example, “Upgrade Spring Boot 2 applications to Spring Boot 3”), and optionally provide a reference repository URL. The creation agent analyzes the source, generates a transformation definition, and publishes it to the ATX registry for reuse across the portfolio.

Describing a custom transformation in plain English. The form accepts a name, description, optional reference repository, and natural-language requirements.

Figure 2: Describing a custom transformation in plain English. The form accepts a name, description, optional reference repository, and natural-language requirements.After submitting, the orchestrator clones the reference repository, analyzes the source, and generates a transformation definition tailored to the actual code patterns found in the codebase. This takes 1–5 minutes depending on repository size. The generated definition is then shown for review in the Jobs tab, where it can be edited before publishing to the ATX registry.

Figure 3: The AI-generated transformation definition shown for review in the Jobs tab. The agent analyzed the Flask codebase and produced a detailed definition covering routes, request handling, response patterns, and Blueprint architecture. The user can edit the definition in-place and click Publish to Registry when ready.Once published, the new transformation appears in the Transformations tab alongside AWS-managed transformations and can be executed the same way on any repository.

Run a batch of repositories from a CSV

Open the CSV Batch tab and upload a CSV listing repository URLs and target transformations. A sample `sample-batch.csv` is included in the repository at `agentic-atx-platform/ui/sample-batch.csv`. The preview shows the parsed rows before submission. On Submit All, each row becomes a separate AWS Batch job running in parallel, and the Jobs tab shows live status as repositories complete.

Uploading a batch of repositories for parallel processing. The CSV lists a source repository URL, target transformation, optional validation commands, and additional plan context per row.

Figure 4: Uploading a batch of repositories for parallel processing. The CSV lists a source repository URL, target transformation, optional validation commands, and additional plan context per row. Each row becomes an independent AWS Batch job on submission.

Clean up

To avoid recurring charges, remove the resources after trying the solution.

Step 1: Delete the SAM Stack

sam delete --stack-name AtxAgentCoreSAM --region us-east-1 --no-prompts

Step 2: Delete the CDK Stacks

Remove the three CDK stacks in reverse order. The S3 buckets are configured with `autoDeleteObjects: true`, so CDK will empty them before deletion.

cd cdk

npx cdk destroy AtxUiStack AtxInfrastructureStack AtxContainerStack --force

Conclusion

In this post, you learned how to build a generative AI–powered, agentic system for application modernization that can analyze application repositories, determine required code changes, create missing transformations, and execute those transformations at scale. By combining AWS Transform Custom for transformation execution with Amazon Bedrock AgentCore for orchestration, and Strands Agents for multi-agent coordination and AWS Transform container solution for parallel processing, this approach demonstrates how intelligent automation can be applied to large-scale code transformation workflows.

This solution directly addresses the challenges of traditional modernization approaches. It reduces manual effort by automating repository analysis and transformation mapping, eliminates gaps in transformation coverage by dynamically generating reusable transformations, and significantly improves scalability through parallel execution using AWS Batch.

By introducing a centralized, agent-driven workflow with built-in observability and state management, organizations can achieve faster, more consistent, and governed modernization across large application portfolios. To get started, deploy the solution in your AWS environment, test it with a sample repository or batch workload, and extend it by creating custom transformations tailored to your applications. You can further integrate this approach into your CI/CD pipelines to enable continuous modernization and accelerate your cloud migration initiatives.


About the authors

Kanishk Mahajan is Principal – AI/ML with AWS Professional Services. In this role, he leads GenAI and agentic transformations for some of AWS largest customers in Telco and Media & Entertaintment.

Sandeep Batchu is a Senior Security Architect at Amazon Web Services, with extensive experience in software engineering, solutions architecture, and cybersecurity. Passionate about bridging business outcomes with technological innovation, Sandeep guides customers through their cloud and generative AI journey, helping them design and implement secure, scalable, and resilient architectures in the era of AI-driven transformation.

Venugopalan Vasudeven (Venu) is a Principal Specialist Solutions Architect at AWS, where he leads Agentic AI initiatives focused on AWS Transform. He helps customers adopt and scale AI-powered developer and modernization solutions to accelerate innovation and business outcomes.

AWS Weekly Roundup: What’s Next with AWS 2026, Amazon Quick, OpenAI partnership, and more (May 4, 2026)

Post Syndicated from Esra Kayabali original https://aws.amazon.com/blogs/aws/aws-weekly-roundup-whats-next-with-aws-2026-amazon-quick-openai-partnership-and-more-may-4-2026/

Last week, I took some time off in York, England, often described as the most haunted city in the country. I wandered through the ruins of abbeys that have stood for nearly a thousand years, walked along medieval walls, and spent an evening on a ghost tour hearing stories passed down through centuries. There’s something grounding about standing in a place that has witnessed so much history. Now I’m back at my desk, and the contrast is hard to miss: those abbey stones have stood for a thousand years largely unchanged, while in the span of a single week away, the pace of technological change has moved forward yet again.

The ruins of Whitby Abbey in North Yorkshire. Stones that have seen a thousand years, while this week alone brought another wave of change.

Now, let’s get into this week’s AWS news.

Headlines
On April 28, Matt Garman, CEO of AWS, Colleen Aubrey, SVP Amazon Applied AI Solutions, Julia White, CMO of AWS, and OpenAI leaders took the stage to share how customers are changing the way businesses operate with agents. The event brought a packed slate of announcements across Amazon Quick, Amazon Connect, and a deeper partnership with OpenAI. Here’s a roundup of the biggest announcements from the event.

Amazon Quick expands with a desktop app, new pricing plans, and visual asset generation – Amazon Quick is an AI assistant for work that connects to your apps, learns what matters to you, and takes action on your behalf. This week, Quick introduced a new desktop app (Preview) that keeps you connected to your local files, calendar, and communications without opening a browser. You can sign up within minutes using your personal email address or existing Google, Apple, Github, or Amazon credentials—no AWS account required. Quick can now generate polished documents, presentations, infographics, and images directly from the chat interface, and native integrations expand to include Google Workspace, Zoom, Airtable, Dropbox, and Microsoft Teams. A new Build custom apps with Quick capability (Preview) lets you create intelligent apps, dashboards, and web pages connected to the rest of your business using natural language.

Amazon Connect expands into four agentic AI solutions – Amazon Connect is expanding from a single product into a set of four agentic AI solutions designed to work within your existing workflows. Amazon Connect Decisions is a supply chain planning and intelligence solution that shifts teams from crisis management to proactive planning, combining 30 years of Amazon operational science with more than 25 specialized supply chain tools. Amazon Connect Talent (Preview) is an agentic AI hiring solution that delivers AI-led interviews, science-backed assessments, and consistent evaluation for talent acquisition leaders managing scaled hiring. Amazon Connect Customer, previously known as Amazon Connect, delivers personalized customer experiences across voice, chat, and digital channels, with new configuration capabilities that enable organizations to set up conversational AI in weeks rather than months. Amazon Connect Health delivers agentic patient verification, appointment management, patient insights, ambient documentation, and medical coding, giving patients faster access to care and clinicians more time to deliver it.

AWS and OpenAI expand their partnership across Amazon Bedrock – AWS and OpenAI are bringing the latest OpenAI models to Amazon Bedrock, launching Codex on Amazon Bedrock, and introducing Amazon Bedrock Managed Agents powered by OpenAI — all in limited preview. OpenAI models on Amazon Bedrock (Limited preview) brings the latest OpenAI models, including GPT-5.5 and GPT-5.4, to the Bedrock APIs you already use, with unified security, governance, and cost controls. No additional infrastructure to configure, no new security model to learn. Codex on Amazon Bedrock (Limited preview) lets you access the OpenAI coding agent within your existing AWS environments, authenticating with your AWS credentials, processing inference through Bedrock, and applying Codex usage toward your AWS cloud commitments. Codex on Bedrock is available through the Bedrock API, starting with the Codex CLI, the Codex desktop app, and a Visual Studio Code extension. Amazon Bedrock Managed Agents, powered by OpenAI (Limited preview) combines OpenAI frontier models with AWS infrastructure to build production-ready OpenAI-powered agents in the cloud, built with the OpenAI harness for faster execution, sharper reasoning, and reliable steering of long-running tasks.

To learn more, visit Top announcements of the What’s Next with AWS, 2026.

Last week’s launches
Here are some launches and updates from this past week that caught my attention:

  • Amazon EC2 M8in and M8ib instances are now generally available – Powered by custom 6th-gen Intel Xeon Scalable processors and 6th-gen AWS Nitro cards, these instances deliver up to 43% higher performance over M6in and M6ib. M8in offers 600 Gbps network bandwidth, while M8ib delivers up to 300 Gbps EBS bandwidth. Available in US East (N. Virginia), US West (Oregon), Asia Pacific (Tokyo), and Europe (Spain).
  • Amazon EC2 R8in and R8ib instances are now generally available – Memory-optimized instances built on the same 6th-gen Intel Xeon Scalable processors and Nitro cards, with the same 600 Gbps network and 300 Gbps EBS bandwidth profiles. Well-suited for large commercial databases, data lakes, and in-memory databases such as SAP HANA. Available in US East (N. Virginia, Ohio), US West (Oregon), and Europe (Spain).
  • Amazon EC2 C8ine and M8ine instances are now generally available – Network-optimized instances offering up to 2.5x higher packet performance per vCPU and up to 2x higher network throughput for traffic through internet gateways compared to C6in and M6in. Designed for security and network virtual appliances including virtual firewalls, load balancers, and 5G UPF workloads. Available in US East (N. Virginia), US West (Oregon), and Asia Pacific (Tokyo) for C8ine; US East (N. Virginia) and US West (Oregon) for M8ine.
  • Amazon Bedrock AgentCore adds optimization capabilities (Preview) – AgentCore now offers recommendations, batch evaluations, and A/B tests to complete the observe-evaluate-improve loop for agents in production. Recommendations analyze production traces and evaluation outputs to propose optimized system prompts and tool descriptions, which you can validate with batch evaluations against pre-defined test cases or A/B tests against live traffic. Every recommendation requires your approval before it ships.
  • AWS Lambda adds support for Ruby 4.0 – Ruby 4.0, the latest LTS release, is available as a Lambda managed runtime and container base image. It includes support for Lambda advanced logging controls, including JSON structured logs, configurable logging levels, and target CloudWatch log group configuration. Available in all AWS Regions, including China Regions and AWS GovCloud (US).

For a full list of AWS announcements, be sure to keep an eye on the What’s New with AWS page.

Other AWS news
Here are some additional posts and resources that you might find interesting:

  • Amazon Q Developer end-of-support announcement – Amazon Q Developer IDE plugins and paid subscriptions will reach end of support on April 30, 2027, giving customers 12 months to transition to Kiro. New signups will be blocked starting May 15, 2026, although existing subscriptions can continue to add users. Starting May 29, 2026, Opus 4.6 will no longer be available on Q Developer Pro; Opus 4.5 and other existing models remain available, and the latest coding models including Opus 4.7 are available exclusively on Kiro. Amazon Q Developer in the AWS Management Console and first-party AWS experiences (documentation, mobile app, Slack, and Microsoft Teams) are not affected.
  • AWS 10,000 AIdeas Competition: Meet the Winners – AWS announced the 20 winners of the 10,000 AIdeas Competition, a global challenge where builders submitted AI applications built entirely with Kiro and the AWS Free Tier, with submissions from 115 countries narrowed down through four rounds of evaluation and two rounds of community voting. Winners span Global Champions, Regional Champions, Innovation Awards, and Creative Track categories, with cash prizes and AWS credits awarded across each tier.
  • AWS Student Builder Groups – AWS Cloud Clubs is evolving to AWS Student Builder Groups. The community now spans 600+ colleges and universities across 63 countries. Existing Cloud Club memberships, badges, and progress carry forward, and Cloud Club Captains become Group Leaders. Membership is open to any learner 18 or older. You can find a group near you on AWS Builder Center or apply to launch a new group on your campus.

Upcoming AWS events
Check your calendar and sign up for upcoming AWS events:

Visit the AWS Builder Center to meet other builders, contribute solutions, and find resources that help you keep building. You can also browse upcoming AWS-led in-person and virtual events, plus developer-focused sessions.

— Esra

This post is part of our Weekly Roundup series. Check back each week for a quick roundup of interesting news and announcements from AWS!

Security posture improvement in the AI era

Post Syndicated from Celeste Bishop original https://aws.amazon.com/blogs/security/security-posture-improvement-in-the-ai-era/

It’s only been a few weeks since Anthropic announced the Claude Mythos Preview model and launched Project Glasswing with AWS and other leading organizations. This has generated a lot of discussion about the future of cybersecurity and what the ever-increasing capabilities of foundation models mean to organizations.

As AWS CISO Amy Herzog pointed out in the Project Glasswing announcement, “At AWS, we build defenses before threats emerge, from our custom silicon up through the technology stack. Security isn’t a phase for us; it’s continuous and embedded in everything we do.”

Read more from Amy about this in Building AI defenses at scale: Before the threats emerge.

While the discussion around the future of cybersecurity is important, the only thing we know for certain is that organizations need to be able to react quickly to the rapid changes AI is bringing to technology and business in general. And you can’t react quickly if your security fundamentals aren’t dialed in.

The security hygiene gap

It’s easy to assume you have the foundational security elements covered, or to overlook some completely. Basic security use cases like identity management, threat detection, vulnerability management, data protection, and network security can be inconsistently implemented across cloud environments. While AI is reshaping the security landscape, strong security fundamentals continue to be essential for every organization, regardless of size or industry.

These are the security basics that matter whether or not you’re adopting AI: patching consistently, enforcing least-privilege access, enabling logging and monitoring, encrypting data at rest and in transit, and reviewing security configurations regularly. When these fundamentals are in place, you’re better positioned to take advantage of AI-driven tools and respond to newly discovered vulnerabilities, wherever they come from.

While the concepts that drive security fundamentals are universal, implementing them in your environment is best done with an understanding of the context unique to your organization. That’s why we have a multitude of freely available materials—like the AWS Well-Architected Framework—that you can use to help ask the right questions and implement changes in your environment. We also offer programs like the Security Health Improvement Program (SHIP) to help you improve your security posture through prescriptive guidance and continuous improvement.

What is the Security Health Improvement Program (SHIP)?

SHIP is a no-cost program available to every AWS customer, regardless of support tier. SHIP provides a proven, data-driven methodology to:

  • Assess your current security posture using data from your AWS environment
  • Identify specific opportunities to improve across 10 core security use cases
  • Build a prioritized action plan tailored to your environment
  • Establish a mechanism for continuous security improvement

The program is led by AWS Solutions Architects and Technical Account Managers who take you through a personalized report, contextualize findings for your environment, and help you build a prioritized action plan.

Why SHIP matters in the AI era

Project Glasswing highlights an important shift: AI-powered tools are accelerating the pace of vulnerability discovery, which means organizations need to be prepared to assess and respond to findings and changing situations faster than before. In addition to external factors, as organizations adopt AI—whether deploying foundation models, building agentic workflows, or using AI-powered services—how they implement their security controls must change as well. A strong security foundation is what makes confident AI adoption possible.

Here’s how SHIP helps:

Address foundational security gaps proactively

SHIP uses a data-driven methodology to identify opportunities to improve and optimize across 10 core security use cases: threat detection, cloud security posture management, application security testing, configuration management, access governance, vulnerability management, application protection, network security, encryption, and secrets management. The program includes a SHIP assessment to identify critical security findings related to your current security posture, so your team can build a prioritized roadmap for improvement tailored to your environment.

Establish the security baseline AI workloads require

Before you deploy your first model on Amazon Bedrock or build agentic workflows with Amazon Bedrock AgentCore, you need confidence that your underlying infrastructure follows security best practices. SHIP uses actual data from your environment to provide prescriptive, specific guidance rather than generic security recommendations. This is especially relevant as AI-driven vulnerability discovery tools become more widely available: organizations with strong baselines will be able to act on new findings quickly and effectively.

Build a mechanism for continuous security improvement

As AI capabilities evolve, organizations benefit from having a repeatable process to assess and strengthen their security posture over time. SHIP establishes the methodology and mechanisms for your team to continuously assess, prioritize, and improve. By building this operational capability, you’re strengthening your organization’s ability to adapt and contributing to broader industry resilience. As the cybersecurity community integrates AI into defense strategies, SHIP helps you maintain foundational best practices so you can adopt these innovations effectively and with confidence.

Getting started is straightforward

SHIP is available today, at no cost, to every AWS customer. Here’s how to get started:

  1. Talk to your AWS account team. Ask about scheduling a SHIP engagement, or request one directly on the SHIP page.
  2. Attend a SHIP Activation Day. AWS regularly hosts hands-on workshops where you can run the SHIP assessment with AWS Solutions Architects and start building your improvement plan.
  3. Explore the prescriptive guidance. Consult the AWS Well-Architected Framework – Security Lens for documentation, reference architectures, and implementation guides you can start using today.

Take the next step together

AWS is committed to being the most secure cloud, from our participation in Project Glasswing to the security embedded in every layer of our infrastructure. Security is a shared responsibility, and programs like SHIP give customers the tools, guidance, and support to strengthen their security foundations so they can build confidently, no matter what comes next.

Ready to improve your security posture? Contact your AWS account team to schedule a SHIP engagement, or visit the SHIP resources page to learn more.

Celeste Bishop

Celeste Bishop

Celeste is a Senior Security Specialist at AWS, based in Austin, Texas. Over the past five years, she has held a range of security-focused roles spanning field and product marketing, developer relations, and executive engagement. She partners closely with customers, security leaders, and field teams to help organizations operate securely in the cloud. Celeste holds a Bachelor’s in Economics from the University of Texas at Austin.

Serverless ICYMI Q1 2026

Post Syndicated from Julian Wood original https://aws.amazon.com/blogs/compute/serverless-icymi-q1-2026/

Stay current with the latest serverless innovations that can improve your applications. In this 32nd quarterly recap, discover the most impactful AWS serverless launches, features, and resources from Q1 2026 that you might have missed.

In case you missed our last ICYMI, check out what happened in Q4 2025.

2026 Q1 calendar

2026 Q1 calendar

Serverless with Mama J




Serverless with Mama J

If you really want to know whether you understand something, try explaining it to your mom!

That’s exactly what Eric Johnson did. His mom, everyone calls her Mama J, wanted to know what serverless actually means and why it matters. So he walked her through it: what servers do, why they’re a headache to manage, and how AWS Lambda lets you skip all that by running code only when it’s needed, scaling automatically, and charging you nothing when nobody’s using it.

Watch the video on the AWS Developers YouTube channel.

Build serverless apps faster with AI

AWS is providing a growing set of AI-powered tools to bring serverless expertise directly into your coding assistants. From Model Context Protocol (MCP) servers and Anthropic Claude plugins to Kiro Powers. These tools provide contextual guidance for architecture decisions, implementation patterns, and deployment automation across the full serverless development lifecycle.

For more information on the tools available, see the resources page.

Serverless Patterns Collection

The open source Serverless Patterns Collection on Serverless Land now provides a direct link to download pattern .zip files. You can also clone the whole repo and explore more patterns.

Serverless Patterns .zip download

Serverless Patterns .zip download

AWS Lambda

Build fault-tolerant, long-running applications using familiar programming patterns using AWS Lambda durable functions. You can use Lambda durable functions to write multi-step workflows in your preferred programming language, using built-in methods that automatically handle progress checkpointing and error recovery. This can improve your architecture so that you can focus on your business logic and optimize costs by charging only for active compute time.

You can build durable functions in Python and TypeScript and there is a durable execution SDK for Java in preview with the code available on GitHub.

Eric Johnson has a new video deep dive showing how to upload videos and scan them with AI. Learn how to coordinate multiple AWS services like Amazon Rekognition and Amazon Transcribe, implement human-in-the-loop approval workflows, and crate a live dashboard for real-time updates.

To find out how durable functions work, see the blog post which also provides testing and best practices guidance. You can also watch the re:Invent Breakout Session video: Deep Dive on AWS Lambda durable functions (CNS380)

Lambda now supports the .NET 10 runtime, including support for file-based apps. Developers can take advantage of the latest .NET 10 performance improvements, new language features, and improved startup times for Lambda functions.

You can now see Availability Zone (AZ) metadata in function execution environments. This allows you to determine the AZ ID (e.g., use1-az1) of the AZ your function is running in. This helps build functions that can make AZ-aware routing decisions, such as preferring same-AZ endpoints for downstream services to reduce cross-AZ latency. Operators can also implement AZ-aware resilience patterns like AZ-specific fault injection testing.

Payload size increase

AWS has increased the maximum payload size from 256 KB to 1 MB for a number of services such as asynchronous Lambda invocations, Amazon SQS, and Amazon EventBridge. This gives you more room to build and maintain context-rich event-driven systems and reduce the need for complex workarounds such as data chunking or external large object storage.

This blog post explores a real-world example using rich event context in agentic event-driven architectures

Payload size increase workflow

Payload size increase workflow

Amazon Bedrock

Amazon Bedrock expanded its model availability with a new set of fully managed open-weight models spanning frontier reasoning and agentic coding. Other model releases include Anthropic Claude Opus 4.6 and Claude Sonnet 4.6, and NVIDIA Nemotron 3 Super. You can invoke them through the unified Amazon Bedrock API without managing any underlying infrastructure, making it straightforward to experiment and swap models as your workload evolves.

Amazon Bedrock AgentCore is the infrastructure layer for securely deploying and operating AI agents. It works with popular open source frameworks, including Strands Agents, LangGraph and CrewAI, giving you the flexibility to build with your preferred tools without vendor lock-in.

AgentCore Gateway now includes semantic tool search, so you can discover the right tool for a task using natural language queries instead of manually browsing a catalogue. It also adds custom KMS encryption, debugging messages, and resource tagging to give you stronger governance over tool integrations.

Policy in Bedrock AgentCore allows you to define precise boundaries on agent actions and run continuous quality monitoring. This helps you maintain predictable, auditable agent behavior in production without embedding guardrail logic inside each individual agent.

AgentCore Runtime now supports stateful MCP server features, allowing agents to maintain session context across tool calls for richer, more coherent multi-step interactions.

Strands Agents

Strands Agents SDK

Strands Agents SDK

Strands Agents is an open source SDK for building and running AI agents in just a few lines of code, working with models available in Amazon Bedrock. Strands Labs is a new dedicated GitHub organization for experimental agent projects, including robotics and code agents. This gives you early access to cutting-edge agentic techniques before they reach production frameworks. See the introduction blog post for more information.

AWS Step Functions

AWS Step Functions introduces an enhanced TestState API that enables API-based testing for validating workflows before deployment. The new API supports testing individual states in isolation or complete workflows end-to-end, making it easier to verify state machine logic without incurring runtime costs.

By integrating TestState API testing into CI/CD pipelines, you can validate workflow logic before deployment, reducing the risk of production issues. Find complete code examples and testing framework in the GitHub repository.

Amazon EventBridge

Amazon EventBridge Scheduler now provides resource count metrics to help you monitor quota usage. These new metrics make it easier to track the number of schedules and schedule groups in your account and proactively manage service quotas.

Amazon DynamoDB

You can replicate Amazon DynamoDB table data across multiple AWS accounts and Regions. This enhances resiliency through account-level isolation, supports tailored security and data-perimeter controls. You can align workloads by business unit or environment and simplify governance requirements.

Amazon DynamoDB global replication

Amazon DynamoDB global replication

Amazon ECS

Amazon ECS Managed Instances can now integrate with Amazon EC2 Capacity Reservations. This allows you to make sure there is capacity availability for your container workloads while benefiting from the management automation of ECS Managed Instances.

ECS also now supports Network Load Balancer (NLB) for linear and canary deployment strategies. This helps you perform gradual traffic shifting using NLBs, providing more flexibility in deployment pipelines for latency-sensitive applications.

Serverless blog posts

January

February

March

Serverless Office Hours

Join our livestream every Tuesday at 11 AM PT for live discussions, Q&A sessions, and deep dives into serverless technologies. Watch episodes on-demand at serverlessland.com/office-hours.

January

February

March

Still looking for more?

The Serverless landing page has overall information about building serverless applications. The Lambda resources page contains case studies, webinars, whitepapers, customer stories, reference architectures, and even more Getting Started tutorials.

You can also follow the Developer Advocacy team to see the latest news, follow conversations, and interact with the team.

And finally, visit Serverless Land  for your serverless needs.

AWS Weekly Roundup: Anthropic & Meta partnership, AWS Lambda S3 Files, Amazon Bedrock AgentCore CLI, and more (April 27, 2026)

Post Syndicated from Daniel Abib original https://aws.amazon.com/blogs/aws/aws-weekly-roundup-anthropic-meta-partnership-aws-lambda-s3-files-amazon-bedrock-agentcore-cli-and-more-april-27-2026/

Late March took me to Seattle for the Specialist Tech Conference, one of the most energizing gatherings of AWS specialists from around the world. It was an incredible opportunity to connect with peers, exchange experiences, and go deep on the latest advancements in Generative AI and Amazon Bedrock — and a powerful reminder of something I truly believe in: when specialists come together to challenge each other, explore edge cases, and co-create solutions, the impact goes far beyond the meeting room. In a fast-moving space like AI, having a strong internal community isn’t a nice-to-have — it’s a competitive advantage.

Now, let’s get into this week’s AWS news…

Headlines

Anthropic partnership: Claude on AWS Trainium and Graviton, and Claude Cowork in Amazon Bedrock – This week, AWS and Anthropic deepened their product collaboration in meaningful ways for builders. Anthropic is now training its most advanced foundation models on AWS Trainium and Graviton infrastructure, co-engineering directly at the silicon level with Annapurna Labs to maximize computational efficiency from the hardware up through the full stack.

Claude Cowork is now available in Amazon Bedrock — Claude Cowork brings Anthropic’s collaborative AI capabilities directly to enterprise builders within the AWS ecosystem, enabling teams to work alongside Claude as a true collaborator, not just a tool. You can now deploy Claude Cowork within your existing Amazon Bedrock environment, keeping your data secure within AWS while leveraging the full power of Claude for team-based AI workflows.

Claude Platform on AWS (Coming soon) — A unified developer experience to build, deploy, and scale Claude-powered applications without leaving AWS. If you’re building with Generative AI on AWS, this is a significant step forward in what you’ll be able to do with Claude directly through Amazon Bedrock.

Meta signs agreement with AWS to power agentic AI on Amazon’s Graviton chips — Meta has signed an agreement to deploy AWS Graviton processors at scale, starting with tens of millions of Graviton cores to power CPU-intensive agentic AI workloads — including real-time reasoning, code generation, search, and multi-step task orchestration.

Last week’s launches

Here are some launches and updates from this past week that caught my attention:

  • AWS Lambda functions can now mount Amazon S3 buckets as file systems with S3 Files — You can now mount Amazon S3 buckets as file systems in AWS Lambda using S3 Files, enabling your functions to perform standard file operations without downloading data for processing. Built on Amazon EFS, S3 Files provides the simplicity of a file system with the scalability, durability, and cost-effectiveness of S3 — and multiple Lambda functions can connect to the same file system simultaneously, sharing data through a common workspace. This is particularly valuable for AI and machine learning workloads where agents need to persist memory and share state across pipeline steps.
  • Amazon EKS Hybrid Nodes gateway for hybrid Kubernetes networking — Amazon Elastic Kubernetes Service now offers the Amazon EKS Hybrid Nodes gateway, which automates networking between your EKS cluster VPC and Kubernetes Pods running on EKS Hybrid Nodes. You can now eliminate the need to make on-premises pod networks routable or coordinate network infrastructure changes, greatly simplifying hybrid Kubernetes environments. The gateway automatically enables pod-to-pod traffic across cloud and on-premises environments, control plane-to-webhook communication, and connectivity for AWS services like Application Load Balancers, and is available at no additional charge.
  • Amazon Aurora Serverless: Up to 30% better performance, smarter scaling, and still scales to zero — Amazon Aurora Serverless just got faster and smarter, with up to 30% better performance than the previous version and an enhanced scaling algorithm designed to handle workloads where multiple tasks compete for resources — like busy APIs and agentic AI applications with bursts of activity and long idle windows. You can now run even more demanding workloads serverlessly, paying only for what you use, and automatically scaling to zero when not in use. All improvements are available in platform version 4 at no additional cost.
  • Amazon Bedrock AgentCore adds new features to help developers build agents faster — Amazon Bedrock AgentCore introduces a managed harness (preview), the AgentCore CLI, and AgentCore skills for coding assistants, helping developers go from idea to working agent prototype faster. The managed harness lets you define an agent by specifying a model, system prompt, and tools and run it immediately with no orchestration code required — and when you’re ready for full control, you can export the harness orchestration as Strands-based code. The AgentCore CLI deploys your agents with the governance and auditability of infrastructure-as-code (AWS CDK today, Terraform coming soon), and is available in 14 AWS Regions at no additional charge.

For a full list of AWS announcements, be sure to keep an eye on the What’s New with AWS page.

Other AWS news

Here are some additional posts and resources that you might find interesting:

  • Introducing granular cost attribution for Amazon Bedrock — This post walks through how Amazon Bedrock’s granular cost attribution works and covers practical example cost tracking scenarios. You can now tag and track Bedrock usage costs at a finer level of detail — useful for organizations running multiple teams or projects on Bedrock who need precise cost visibility and chargeback capabilities.
  • Automating Incident Investigation with AWS DevOps Agent and Salesforce MCP Server — This post (co-written with Salesforce) shows how AWS DevOps Agent, integrated with the Salesforce MCP Server, automates the full lifecycle of infrastructure incident investigation — from identifying issues and diagnosing root causes to notifying customers through Salesforce Service Cloud. It’s a compelling real-world example of how AI agents and MCP-based tool connectivity are reshaping DevOps workflows in production, dramatically reducing mean time to resolution.
  • Microcredentials from AWS are now free — Here’s why that matters — You can now access AWS microcredentials at no cost through AWS Skill Builder in all countries where the platform is offered. Unlike traditional multiple-choice certifications, microcredentials are hands-on assessments that place builders in simulated business scenarios where they configure, troubleshoot, and optimize directly in a live AWS environment — the same way they would on the job. A great opportunity to validate real cloud skills without a cost barrier.
  • Amazon SageMaker AI now supports optimized generative AI inference recommendations — You can now use Amazon SageMaker AI to automatically identify optimized deployment configurations for your generative AI models, including instance type, container, and inference parameters. This new capability takes the guesswork out of tuning inference infrastructure, helping you reduce costs and improve latency for your AI applications in production.

Upcoming AWS events

Check your calendar and sign up for upcoming AWS events:

  • What’s Next with AWS — Tune in on April 28 for What’s Next with AWS, a virtual event featuring the latest announcements and product updates directly from AWS teams. A great opportunity to get up to speed on what’s new before diving into the week’s launches.
  • AWS Summits — AWS Summits are free in-person events where you can explore the latest in cloud and AI innovation, learn best practices, and network with builders and experts. Coming up in May: Singapore (May 6), Tel Aviv (May 6), Warsaw (May 6), Stockholm (May 7), Sydney (May 13–14), Hamburg (May 20), Seoul (May 20), Amsterdam (May 27), Bangkok (May 28), Milan (May 28), and Mumbai (May 28). And in June, join us in Los Angeles (June 10). Check the full schedule and register at the link above.
  • AWS Community Days — Community-led conferences where content is planned, sourced, and delivered by community leaders, featuring technical discussions, workshops, and hands-on labs. Upcoming events include Athens, Greece (April 28), Vancouver, Canada (May 1), İstanbul, Türkiye (May 9), and Panama City, Panama (May 23). If you’re in Latin America, mark your calendar for the AWS Community Day Belo Horizonte (August 22) — registration is open at awscommunityday.com.br.

Join the AWS Builder Center to connect with builders, share solutions, and access content that supports your development. Browse here for upcoming AWS-led in-person and virtual events and developer-focused events.

That’s all for this week. Check back next Monday for another Weekly Roundup!

— Daniel Abib

This post is part of our Weekly Roundup series. Check back each week for a quick roundup of interesting news and announcements from AWS!