Tag Archives: Amazon Connect

Set up custom domains in Amazon Connect hosted with M365 Exchange Online or Google Workspace

Post Syndicated from Zip Zieper original https://aws.amazon.com/blogs/messaging-and-targeting/set-up-custom-domains-in-amazon-connect-hosted-with-m365-exchange-online-or-google-workspace/

Amazon Connect Email provides built-in capabilities that make it straightforward to prioritize, assign, and automate the resolution of customer service emails, improving customer satisfaction and agent productivity. With Amazon Connect Email, you can receive and respond to emails sent by customers to business addresses or submitted through web forms on your website or mobile app. You can configure auto-responses, prioritize emails, create or update cases, and route emails to the best available agent when agent assistance is required. Additionally, these capabilities work seamlessly with Amazon Connect outbound campaigns, helping you deliver proactive and personalized email communications.

Amazon Connect Email integrates with Amazon Simple Email Service to send, receive, and monitor emails for content marked as spam or containing viruses, delivery success rates, and sender reputation results.

This post guides you through setting up email in Amazon Connect by routing emails from your email server (Microsoft 365 or Google Workspace) to Amazon Simple Email Service (Amazon SES) SMTP endpoints using a custom email domain onboarded to Amazon SES. By configuring Amazon Connect with your custom email domain in Amazon SES, you can create a unified communication hub that enhances customer experience while simplifying agent workflows. The result is a more responsive, efficient contact center that meets customers where they are, whether they prefer speaking, chatting, or sending emails.

Use case overview

AnyCompany has invested heavily in its email infrastructure over the years, developing a robust and centralized email server that manages both internal and external email traffic. This unified system has become an integral part of their operations, streamlining communication across departments and with customers. AnyCompany has also established a public support email address that has gained significant recognition and trust among their customer base. This email address, featured prominently in all their product documentation, marketing materials, and customer communications, has become a cornerstone of their brand identity in customer support.

Now, AnyCompany faces the challenge of enhancing their customer support process by implementing an automated acknowledgment system for incoming support emails. However, they want to maintain their existing email setup due to its deep integration with internal workflows and the substantial investment it represents. Additionally, preserving their well-known support email address is crucial to protect the brand equity they’ve built over years of customer interactions.

By integrating Amazon Connect with their current email server, AnyCompany can create a seamless solution that addresses these complex requirements. With this integration, customers can continue sending emails to the familiar public support address (for example, [email protected]), maintaining consistency in their customer experience. When new emails are received, Amazon Connect can trigger automated acknowledgment messages, providing immediate assurance to customers that their inquiries have been received and are being processed.

This approach offers multiple benefits. It improves customer satisfaction by providing prompt responses and reduces the volume of follow-up emails. It also preserves AnyCompany’s significant investment in their existing email infrastructure, so they can continue using the centralized system for both internal and external communications. Perhaps most importantly, it maintains the brand recognition associated with their long-standing support email address, so customers can continue to use the contact point they’ve grown to trust over the years.

Solution overview

This post provides a contact center email solution with the following benefits:

  • Customers continue to send emails to your custom domain
  • Emails are routed through your primary email server to Amazon Connect (via Amazon SES)
  • Agents receive and respond to emails within the Amazon Connect agent workspace
  • Customers receive agent responses from your custom domain (via Amazon SES)

This solution involves three main steps:

  1. Configure Microsoft 365 or Google Workspace to route emails to Amazon Connect
  2. Verify your custom domain in Amazon SES to enable sending emails
  3. Onboard your email address in Amazon Connect to handle customer communications

Prerequisites

Before you begin, make sure you have the following prerequisites:

  • Administrative access to modify your custom email domain’s DNS settings.
    • Note – modifying MX records can impact email receiving for your primary domain (example.com). It is highly recommended to create a subdomain (for example, testing.example.com) for testing to avoid impacting any email receiving on your primary domain or use the provided email domain that comes with the Amazon Connect instance (for example, @<instance-alias>.email.connect.aws).
  • Administrative access to modify your Microsoft 365 Exchange Online or Google Workspace Gmail configuration.
  • AWS Identity and Access Management (IAM) access to Amazon SES and Amazon Connect on your AWS Management Console.
  • An existing user in Amazon Connect with access to managing email flows, channels, and routing. For example, CallCenterManager can be used to perform actions related to user management, metrics, and routing. Or you can create a user with a custom scoped-down security profile.
  • When setting up Amazon Simple Email Service for use with Amazon Connect your SES account will be in the sandbox mode, which works well for testing. You will need to request Amazon SES production access before you can fully utilize Amazon SES with Amazon Connect.

Configure Amazon SES

Part of creating a domain identity is configuring its DKIM-based verification. DomainKeys Identified Mail (DKIM) is an email authentication method that Amazon SES uses to verify domain ownership, and receiving mail servers use to validate email authenticity. To learn more, refer to Creating a domain identity.

Complete the following steps to configure your domain identity in Amazon SES:

  1. Open your AWS console and choose the AWS Region where your Amazon Connect instance is deployed.
  2. On the Amazon SES console, choose Identities under Configuration in the navigation pane.
  3. Choose Create identity and provide the following information:
    1. Choose Domain as the identity type.
    2. Enter your custom email domain name.
    3. Enable Use a custom MAIL FROM domain.
    4. Set MAIL FROM domain to feedback.
    5. Set Behavior on MX failure to Use default MAIL FROM domain.
  4. For DKIM verification, provide the following information (unless instructed otherwise):
    1. Choose Easy DKIM under Advanced DKIM settings.
    2. Choose RSA_2048_BIT for DKIM signing key length.
    3. Enable Publish DNS records to Route53 if applicable.
    4. Enable DKIM signatures.
  5. Choose Create identity.

Amazon SES will generate DNS records needed to verify the domain, including:

  • DKIM CNAME records
  • Custom MAIL FROM domain MX and TXT records
  • DMARC TXT records

If the domain is hosted in Route 53, Amazon SES provides an option to automatically Publish DNS records to Route53. When your domain is hosted with Route 53, SES domain verification typically completes within a few minutes. You will see the status Verification pending, followed by Verified.

If the domain is not hosted in Route53, Amazon SES will present individual copy buttons per record as well as a CSV file download option. These records must be added to your DNS so Amazon SES can verify the domain.

After your externally managed DNS has been updated, return to the Amazon SES console and confirm that the identity status has changed to Verified. The time to complete this step is highly variable. You can choose to configure DKIM by using either Easy DKIM or Bring Your Own DKIM (BYODKIM), and depending on your choice, you will have to configure the signing key length of the private key. For detailed steps, refer to Creating a domain identity.

When you first setup Amazon SES, your account is placed in the SES sandbox which we use to prevent unauthorized or unintended sending. While in sandbox mode, you can only send mail to email addresses and domains you verify. After you receive Amazon SES production access for your custom domain, you can send and receive email to and from a valid email address without verification. For more information about the Amazon SES sandbox, refer to Request production access (Moving out of the Amazon SES sandbox).

For setup and testing purposes, complete the following steps to configure an email identity in Amazon SES:

  1. On the Amazon SES console, choose Identities under Configuration in the navigation pane.
  2. Choose Create identity and choose Email Address.
  3. Enter your work email address (you will need access to the inbox to verify ownership). This is the email address that Amazon Connect and Amazon SES will use to send and receive email while your SES account is in the sandbox.
  4. Click Create identity.
  5. Check your email inbox and click the link to verify this is an email address you control.

Configure Amazon Connect

Complete the following steps to configure Amazon Connect:

  1. On the Amazon Connect console, open your instance by clicking on Instance alias.
  2. Under Channels and communications, choose Email.
  3. Choose Add domain.
  4. Choose the domain you verified in Amazon SES.
  5. In your instance, choose Email addresses under Channels.
  6. Choose Create email address and provide the following information:
    1. Create an email address with the same name and domain as the inbound address your customers will use ([email protected]).
    2. Provide a friendly sender name that will appear in customer inboxes.
    3. Create a new flow or attach an existing flow to the custom domain email address (this flow will route inbound emails).
    4. Choose Save.
  7. Configure Outbound email configuration in your outbound queue:
    1. For Default email address, provide the email address you created earlier.
    2. For Outbound email flow, provide the email flow for outbound emails (this flow will route outbound emails).
    3. Choose Save.

Configure Microsoft 365 Exchange or Google Workspace

In this section, we provide step-by-step guidance to configure your primary email service with a rule (Microsoft) or route (Google) that sends inbound email addressed to a specific address(s) to Amazon Connect.

Option A: Microsoft 365 Exchange configuration

Complete the following steps to configure Microsoft 365 Exchange:

  1. Find the email receiving endpoint for your Region. For example, inbound-smtp.us-west-2.amazonaws.com.
  2. Create a connector in Exchange:
    1. Navigate to the Exchange admin center.
    2. Under Mail flow, choose Connectors.
    3. Choose Add a connector.
    4. Set Connection from to Office 365
    5. Set Connection to to Your organization’s email server.
    6. Choose Next.
    7. Name the connector to identify the Region.
    8. Choose Next.
    9. For Use of connector, select Only when I have a transport rule set up that redirects messages to this connector.
    10. For Routing, enter the SES email receiving endpoint.
    11. Choose the plus sign, then choose Next.
    12. For Security restrictions, select Always use Transport Layer Security (TLS) to secure the connection.
    13. Follow your internal process for this step. In this example, we select Any digital certificate, including self-signed certificates.
    14. Choose Next.
    15. For Validation email, enter a valid email address currently used in your Amazon Connect instance.
    16. Choose the plus sign, then choose Next.
      This will send a test email address to that email address. No action needs to be taken with the test email. You should see the email validated and receive the validation test email in the agent workspace.
    17. Review your connector configuration and choose Create connector.

Validate that the connector status is set to On, then proceed to the next steps.

  1. Create a mail flow rule to send your inbound email to Amazon Connect:
    1. Under Mail flow, choose Rules.
    2. Choose Add a rule¸ then choose Create a new rule.
    3. Name the rule.
    4. Set conditions to apply if the recipient is this person and choose the email address for Amazon Connect.
    5. Set the action to Redirect the message to and the following connector and choose your new connector.
    6. Choose Next.
    7. Set Rule mode to Enforce.
    8. Activate the rule immediately by specifying the current time.
    9. Set Match sender address in message to Header or envelope.
    10. Choose Next.
    11. Review your rule configuration and choose Finish.

After you confirm your rule is enabled, you can test your configuration.

Option B: Google Workspace Gmail configuration

Complete the following steps to configure with Google Workspace:

  1. Log into your Google Workspace admin account.
  2. Navigate to Gmail.
  3. Choose Hosts and choose Add Route.
  4. Configure the mail route:
    1. Provide a name indicating the Region.
    2. Enter the SES email receiving endpoint and port 25.
    3. Enable security options:
      1. Select Require mail to be transmitted via a secure (TLS) connection.
      2. Select Require CA signed certificate.
      3. Select Validate certificate hostname.
    4. Choose Test TLS connection.
    5. If the connection is successful, choose SAVE.
  5. Configure default routing:
    1. Navigate to Default routing and choose Configure.
    2. Enter the email address that should route to Amazon Connect.
    3. Change the route to the mail route you created.
    4. Select Perform this action on non-recognized and recognized addresses.
    5. Save and confirm the route is enabled.

Test your configuration

After you have completed the appropriate steps above, test both inbound (to Amazon Connect) and outbound (from Amazon Connect) message-flows.

Test inbound (to Amazon Connect)

Test your inbound configuration:

  1. Open your email application.
  2. Send a test email to the email address you configured to be sent to Amazon Connect.
  3. In the Amazon Connect agent workspace, accept the incoming email.
  4. Confirm the email received in your agent workspace matches the email address you configured to be sent to Amazon Connect.

Test outbound (to external recipient from Amazon Connect)

Test your outbound configuration:

  1. Log in to your Amazon Connect instance.
  2. Choose New email.
  3. Enter To address (use your work email address), Subject & Body.
    1. Alternatively, To address (use your work email address) and choose a Template.
  4. Click Send.
  5. Check your work email inbox for the message. Verify the email’s From address is the email address you configured to be sent from Amazon Connect.

Request Amazon SES production access

Once you have successfully tested email receiving and sending within Amazon Connect, request Amazon SES production access (see Moving out of the Amazon SES sandbox) in the Amazon SES Developer Guide. Importantly, you will not be able to send email from your domain via Amazon Connect until your account is removed from the SES sandbox.

Conclusion

In this post, we showed how to configure Amazon Connect to handle emails using your custom domain through Microsoft 365 or Google Workspace. This setup provides a seamless email experience for your customers while giving your agents the powerful tools available in the Amazon Connect agent workspace.

To get started with Amazon Connect Email, refer to the Amazon Connect Administrator Guide. For hands-on learners, the Amazon Connect Email Enablement Workshop provides guidance and exercises to configure Amazon Connect Email, set up email queues and routing rules, and discusses best practices for delivering exceptional email-based customer service.

Additional resources

For additional guidance and information, refer to the following resources:

About the authors

AWS Weekly Roundup: Amazon DocumentDB, AWS Lambda, Amazon EC2, and more (August 4, 2025)

Post Syndicated from Danilo Poccia original https://aws.amazon.com/blogs/aws/aws-weekly-roundup-amazon-documentdb-aws-lambda-amazon-ec2-and-more-august-4-2025/

This week brings an array of innovations spanning from generative AI capabilities to enhancements of foundational services. Whether you’re building AI-powered applications, managing databases, or optimizing your cloud infrastructure, these updates help build more advanced, robust, and flexible applications.

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

Additional updates
Here are some additional projects, blog posts, and news items that I found interesting:

Upcoming AWS events
Check your calendars so that you can sign up for these upcoming events:

AWS re:Invent 2025 (December 1-5, 2025, Las Vegas) — AWS’s flagship annual conference offering collaborative innovation through peer-to-peer learning, expert-led discussions, and invaluable networking opportunities.

AWS Summits — Join free online and in-person events that bring the cloud computing community together to connect, collaborate, and learn about AWS. Register in your nearest city: Mexico City (August 6) and Jakarta (August 7).

AWS Community Days — Join community-led conferences that feature technical discussions, workshops, and hands-on labs led by expert AWS users and industry leaders from around the world: Australia (August 15), Adria (September 5), Baltic (September 10), and Aotearoa (September 18).

Join the AWS Builder Center to learn, build, and connect with builders in the AWS community. Browse here upcoming in-person and virtual developer-focused events.

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

– Danilo

AWS Weekly Roundup: EC2 C8gn instances, Amazon Nova Canvas virtual try-on, and more (July 7, 2025)

Post Syndicated from Elizabeth Fuentes original https://aws.amazon.com/blogs/aws/aws-weekly-roundup-amazon-bedrock-api-keys-amazon-nova-canvas-virtual-try-on-and-more-july-7-2025/

Every Monday we tell you about the best releases and blogs that caught our attention last week.

Before continuing with this AWS Weekly Roundup, I’d like to share that last month I moved with my family to San Francisco, California, to start a new role as Developer Advocate/SDE, GenAI.

This excites me because I’ll have the opportunity to connect with new communities in the Bay Area while tackling exciting new challenges. If you’re part of a community focused on building generative AI and agentics applications, or know of one, I’d love to connect. Let’s connect!

Last week’s launches
Here are the launches from last week:

  • New Amazon EC2 C8gn instances powered by AWS Graviton4 offering up to 600Gbps network bandwidth – Amazon Elastic Compute Cloud (Amazon EC2) C8gn instances are now generally available, powered by AWS Graviton4 processors and 6th generation AWS Nitro Cards. These network-optimized instances deliver up to 600 Gbps network bandwidth. This represents the highest bandwidth among EC2 network-optimized instances, with up to 192 vCPUs and 384 GiB memory. They provide 30% higher compute performance than C7gn instances and are ideal for network-intensive workloads like virtual appliances, data analytics, and cluster computing jobs.
  • Build the highest resilience apps with multi-Region strong consistency in Amazon DynamoDB global tables – Amazon DynamoDB global tables now supports multi-Region strong consistency (MRSC) for applications requiring zero Recovery Point Objective (RPO). This capability ensures applications can read the latest data from any Region during outages, addressing critical needs in payment processing and financial services. MRSC requires three AWS Regions configured as either three full replicas or two replicas plus a witness, providing the highest level of application resilience for mission-critical workloads.
  • Amazon Nova Canvas update: Virtual try-on and style options now available – Amazon Nova Canvas introduces virtual try-on capabilities that help you visualize how clothing looks on a person by combining two images, plus eight new pre-trained style options (3D animation, design sketch, vector illustration, graphic novel, etc.) for generating images with improved artistic consistency. Available in three AWS Regions, these features enhance AI-powered image generation capabilities for retailers and content creators seeking realistic product visualizations.
  • Amazon Q in Connect now supports 7 languages for proactive recommendations – Amazon Q in Connect, a generative AI-powered assistant for customer service, now provides proactive recommendations in seven languages: English, Spanish, French, Portuguese, Mandarin, Japanese, and Korean. The AI-powered customer service assistant detects customer intent during voice and chat interactions to help agents resolve issues quickly and accurately.
  • Amazon Aurora MySQL and Amazon RDS for MySQL integration with Amazon SageMaker is now available – This integration provides near real-time data availability for analytics. It automatically extracts MySQL data into lakehouses with Apache Iceberg compatibility. You can then access this data seamlessly through various analytics engines and machine learning tools.
  • Amazon Aurora DSQL is now available in additional AWS Regions – Amazon Aurora DSQL expands to Asia Pacific (Seoul) and now supports multi-Region clusters across Asia Pacific and European regions. This serverless, distributed SQL database offers unlimited scalability, highest availability, and zero infrastructure management with AWS Free Tier access.

Other AWS blog posts

  • Optimize RAG in production environments using Amazon SageMaker JumpStart and Amazon OpenSearch Service – Learn how to optimize Retrieval Augmented Generation (RAG) in production environments using Amazon SageMaker JumpStart and Amazon OpenSearch Service. This comprehensive guide demonstrates implementing RAG workflows with LangChain, covers OpenSearch optimization strategies, provides setup instructions, and explains benefits of combining these AWS services for scalable, cost-effective generative AI applications.v
  • Agentic GenAI App Using Bedrock, MCP servers on EKS – This post shows how to build a scalable AI chat application using Amazon Bedrock, Strands Agent, and Model Context Protocol (MCP) servers deployed on Amazon Elastic Kubernetes Service (Amazon EKS). The architecture combines agentic workflows with containerized microservices for intelligent, auto-scaling conversations with multiple foundation models.
  • Enforce table level access control on data lake tables using AWS Glue 5.0 with AWS Lake Formation – AWS Glue 5.0 introduces Full-Table Access (FTA) control for Apache Spark with AWS Lake Formation, providing table-level security without fine-grained access overhead. This feature supports native Spark SQL/DataFrames for Lake Formation tables. It enables read/write operations on Iceberg and Hive tables with improved performance and lower costs.

Upcoming AWS events
Check your calendars and sign up for these upcoming AWS events:

  • AWS re:Invent – Register now to get a head start on choosing your best learning path, booking travel and accommodations, and bringing your team to learn, connect, and have fun. Early-career professionals can apply for the All Builders Welcome Grant program, designed to remove financial barriers and create diverse pathways into cloud technology. Applications are now open and close on July 15, 2025.
  • AWS NY Summit – You can gain insights from Swami’s keynote featuring the latest cutting-edge AWS technologies in compute, storage, and generative AI. My News Blog team is also preparing some exciting news for you. If you’re unable to attend in person, you can still participate by registering for the global live stream. Also, save the date for these upcoming Summits in July and August near your city.
  • AWS Builders Online Series – If you’re based in one of the Asia Pacific time zones, join and learn fundamental AWS concepts, architectural best practices, and hands-on demonstrations to help you build, migrate, and deploy your workloads on AWS.
  • Join AWS Gen AI Lofts – Experience AWS Gen AI Lofts across San Francisco, Berlin, Dubai, Dublin, Bengaluru, Manchester, Paris, Tel Aviv, and additional locations – hands-on workshops, expert guidance, investor networking, and collaborative spaces designed to accelerate your generative AI startup journey.

You can browse all upcoming in-person and virtual events.

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

— Eli

Training a call center fraud detection model for IVR calls with Amazon SageMaker Canvas

Post Syndicated from Pablo Forero original https://aws.amazon.com/blogs/architecture/training-a-call-center-fraud-detection-model-for-ivr-calls-with-amazon-sagemaker-canvas/

Fraud detection is a critical challenge for call centers, they need to provide a seamless customer experience while protecting the organization from fraudulent activities. Traditionally, call centers have relied on agents to manually screen calls, which can be time-consuming and expensive. Alternatively, companies might force customers to authenticate themselves every time they call, leading to a poor user experience. Machine learning (ML) offers a powerful solution that can help organization reach a harmonious balance between these approaches, enabling efficient and accurate fraud detection without compromising the customer experience.

This blog post will show you how to use the power of ML to build a fraud-detection model using Amazon SageMaker Canvas, a no-code/low-code ML service that business analysts and domain experts can use to build, train, and deploy ML models without requiring extensive ML expertise.

Background

In this solution, you will use a contact trace record (CTR) dataset from Amazon Connect. The solution works with data from other inbound telephony services provided they contain call specific metadata. Importantly, each call has been previously labeled based on past fraud detection efforts by the call center.

To start, you will enrich the raw CTR data using the phone number validation service from Amazon Pinpoint. Then, you will prepare the data using Amazon SageMaker notebooks and train a fraud detection model using SageMaker Canvas. Finally, to understand how to provide a scalable and cost-effective solution, you will explore how to deploy the model to a Sagemaker endpoint and right-size through autoscaling in a managed, serverless environment.

The following figure shows the architecture with the complete process including data enrichment, merging, cleanup, and model training and deployment. Throughout this blogpost we will reference the key parts as we implement them.

Architecture diagram

Data enrichment and preparation

Each CTR contains information about an incoming call such as agent, connection attempts, and channel. Before proceeding, you must transform the data into a tabular form (CSV, Parquet, or tables), which are the supported formats in SageMaker Canvas.

The raw CTR dataset doesn’t contain enough information to effectively train an ML model. You will enrich it using the Amazon Pinpoint validate API, which provides additional fields such as carrier, location data, and phone type. After you have the enriched dataset, you can use a SageMaker notebook to clean and prepare the data for training.

Enriching the data with Amazon Pinpoint validate API
Amazon Pinpoint includes a phone number validation service that you can use to determine if a phone number is valid and to obtain additional contact information. For example, the API response for a valid mobile phone number would look like the following:

{
    "NumberValidateResponse": {
        "Carrier": "ExampleCorp Mobile",
        "City": "Seattle",
        "CleansedPhoneNumberE164": "+12065550142",
        "CleansedPhoneNumberNational": "2065550142",
        "Country": "United States",
        "CountryCodeIso2": "US",
        "CountryCodeNumeric": "1",
        "OriginalPhoneNumber": "+12065550142",
        "PhoneType": "MOBILE",
        "PhoneTypeCode": 0,
        "Timezone": "America/Los_Angeles",
        "ZipCode": "98101"
    }
}

While the response for an invalid phone number would contain the following:

{
    "NumberValidateResponse": {
        "CleansedPhoneNumberE164": "+44163296076",
        "CleansedPhoneNumberNational": "163296076",
        "Country": "United Kingdom",
        "CountryCodeIso2": "GB",
        "CountryCodeNumeric": "44",
        "OriginalPhoneNumber": "+440163296076",
        "PhoneType": "INVALID",
        "PhoneTypeCode": 3
    }
}

There are multiple ways to enrich your dataset with this API. The response from the validate API call is a JSON document that contains all the fields. You will need to convert them to the appropriate format and merge them with the original CTR dataset. This will give you an enriched dataset that includes all the fields from the CTR and their corresponding validate results. The goal is to extract the caller phone number from each row in the dataset (CustomerEndpoint in Connect) and run it against the Amazon Pinpoint validate API.

The following figure shows an example architecture used to enrich with Amazon Pinpoint, cache in Amazon DynamoDB, and merge the datasets with Lambda functions. The DynamoDB cache saves the responses from Pinpoint by input key so that you don’t have to re-validate phone numbers.

Portion of the architecture focusing on the validation process

Data engineering and data preparation

The first step is to clean up the data by discarding fields that aren’t adding any predictive value. This will make the training process faster and the model more accurate. For example, in the CTR data, the AWSAccountId field will be the same for all records, and the ContactId field will be unique, so you can discard them both. The goal is to simplify the dataset as much as possible using SageMaker Canvas to perform multiple experiments to better understand which fields in the data have the biggest impact on the prediction.

After you have reduced the dataset, you can select a random, smaller subset of data (for example, 1,000 records) and build a model in SageMaker Canvas. SageMaker Canvas provides a visual interface that you can use to rapidly build, train, and deploy ML models without the need for extensive coding.

To begin the training process, you will first import the prepared, enriched data file containing the CTR data into SageMaker Canvas. SageMaker Canvas will automatically detect the data format and structure, allowing you to preview the dataset and make any necessary adjustments before proceeding.

After the dataset is ready, you can select the fraud label as your target variable and configure the model training parameters. SageMaker Canvas will handle the underlying ML algorithms and hyperparameter tuning, streamlining the model development process.

After the model is trained, SageMaker Canvas will show an analysis of the fields and their weights. In addition to the build step—where you can drop and transform your imported dataset—SageMaker Canvas also includes Amazon SageMaker Data Wrangler, which you can use to prepare, featurize, and analyze your data. This allows you to do additional transformations as you experiment and iterate. You should continue to run these small experiments while making changes to the training dataset with the goal of getting the best performance from your model, while reducing the training time and the latency in inference.

After experimenting, you will identify the most important features and how you want to transform your data. When you’re confident in your model’s performance, you can decide how to deploy the trained model.

Final model deployment and right-sizing

Once your model is trained, you will need to deploy an endpoint so that you can invoke your model and consume the results via API. For example, the diagram below shows a Lambda Function calling the deployed endpoint. We continue to use the DynamoDB table as a cache. This way we avoid reprocessing numbers.

Portion of the architecture focusing on SageMaker model invocation

SageMaker Canvas offers a default deployment option where you can choose the instance type and number of instances to host the trained model that will meet your scaling needs. To help ensure that these instances aren’t over- or under-provisioned, SageMaker provides multiple features to help you optimize your deployment to your specific needs.

  • Autoscaling: Autoscaling dynamically adjusts the number of instances provisioned for a model in response to workload changes. The steps to make this change are described in detail in Configure model autoscaling. SageMaker recently introduced Scale Down to Zero for AI inference, which allows endpoints to scale to zero instances during periods of inactivity and can help customers save costs.
  • Inference recommender: Amazon SageMaker Inference Recommender reduces the time required to get ML models into production by automating load testing and model tuning across SageMaker ML instances.
  • Serverless deployment: Amazon SageMaker Serverless Inference is a purpose-built inference option that you can use to deploy and scale ML models without configuring or managing any of the underlying infrastructure. Compute resources scale automatically depending on traffic, eliminating the need to choose instance types or manage scaling policies. To learn more, see Serverless endpoint operations.

To have use a serverless deployment and obtain inference recommendations, a single-container model is needed. This is currently not possible when using SageMaker Data Wrangler, because it generates two containers following data transformation: one for data preprocessing and one for model prediction.

After preparing the final dataset, you can bring it into SageMaker Canvas to train the detection model. Follow the same steps as you did with the smaller tests, making sure that you don’t use any of the data transformation options within SageMaker Canvas.

Depending on the size and complexity of the final dataset, the training process can take several hours to complete. After the training is complete, SageMaker Canvas will generate a trained model that you can immediately deploy to an endpoint.

Conclusion

By using the power of Amazon SageMaker Canvas, you can build, train, and deploy a robust fraud detection model, empowering your call center to deliver exceptional customer experiences while safeguarding your business and allowing your human agents to focus on legitimate customers.

You can begin testing SageMaker Canvas using the AWS Management Console today or learn more about SageMaker Canvas basics at the SageMaker Canvas Immersion Day workshop.

About the authors

AWS Weekly roundup: EventBridge, SNS FIFO, Amazon Corretto, Amazon Connect, Amazon Bedrock, and more

Post Syndicated from Sébastien Stormacq original https://aws.amazon.com/blogs/aws/aws-weekly-roundup-eventbridge-sns-fifo-amazon-corretto-amazon-connect-amazon-bedrock-and-more/

I counted about 40 new launches from AWS since last week – back to our normal rhythm of releases. Services teams are listening to your feedback and developing little (or big) changes that makes your life easier when working with our services. The ability to support multiple sessions in the AWS Console is my favorite one so far in 2025.

But our teams didn’t stop there, let’s look at the last week’s new announcements.

Last week’s launches

Beside the usual Regional expansion (new capabilities that are now available in a new Region), here are the launches that got my attention.

Amazon EventBridge announces direct delivery to cross-account targets – Amazon EventBridge is now able to deliver events to targets in another AWS account directly without having to send them to the default bus in the target account first. This will simplify so many architectures out there! It supports any target that supports resource-based policies, including AWS Lambda, Amazon Simple Queue Service (Amazon SQS), Amazon Simple Notification Service (Amazon SNS), Amazon Kinesis, and Amazon API Gateway.

Amazon Corretto quaterly update – We announced quarterly security and critical updates for Amazon Corretto Long-Term Supported (LTS) and Feature Release (FR) versions of OpenJDK. Corretto 23.0.2, 21.0.6, 17.0.14, 11.0.26, 8u442 are now available for download. Amazon Corretto is a no-cost, multi-platform, production-ready distribution of OpenJDK. You can download the updates from the Corretto home page or just type apt-get or yum update.

High-throughput mode for Amazon SNS FIFO Topics – Amazon SNS now supports high-throughput mode for SNS FIFO topics, with default throughput matching SNS standard topics across all Regions. When you enable high-throughput mode, SNS FIFO topics will maintain order within message group, while reducing the deduplication scope to the message-group level. With this change, you can leverage up to 30K messages per second (MPS) per account by default in US East (N. Virginia) Region, and 9K MPS per account in US West (Oregon) and Europe (Ireland) Regions, and request quota increases for additional throughput in any Region.

Amazon Connect agent workspace now supports audio optimization for Citrix and Amazon WorkSpaces virtual desktops – Amazon Connect agent workspace now supports the ability to redirect audio from Citrix and Amazon WorkSpaces Virtual Desktop Infrastructure (VDI) environments to a customer service agent’s local device. Audio redirection improves voice quality and reduces latency for voice calls handled on virtual desktops, providing a better experience for both end customers and agents.

Amazon Redshift announces support for History Mode for zero-ETL integrations – This new capability enables you to build Type 2 Slowly Changing Dimension (SCD 2) tables on your historical data from databases, out-of-the-box in Amazon Redshift, without writing any code. History mode simplifies the process of tracking and analyzing historical data changes, allowing you to gain valuable insights from your data’s evolution over time.

Finally, Amazon Bedrock has its own set of announcements. First, for anyone investing in retrieval-augmented generation, Bedrock now support multimodal content with Cohere Embed 3 Multilingual and Embed 3 English models. This enables you to create embeddings to not only index text, but also images.

Second, read Luma AI’s Ray2 visual AI model now available in Amazon Bedrock. Luma Ray2 is a large-scale video-generation model capable of creating realistic visuals with fluid, natural movement. With Luma Ray2 in Amazon Bedrock, you can generate production-ready video clips with seamless animations, ultrarealistic details, and logical event sequences with natural language prompts, removing the need for technical prompt engineering. Ray2 currently supports 5- and 9-second video generations with 540p and 720p resolution.

And finally, Amazon Bedrock Flows announces preview of multi-turn conversation support. Amazon Bedrock Flows enables you to link foundation models (FMs), Amazon Bedrock Prompts, Amazon Bedrock Agents, Amazon Bedrock Knowledge Bases, Amazon Bedrock Guardrails and other AWS services together to build and scale pre-defined generative AI workflows. This week, the team announced preview of multi-turn conversation support for agent nodes in Flows. This capability enables dynamic, back-and-forth conversations between users and flows, similar to a natural dialogue.

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

Other AWS events
Check your calendar and sign up for upcoming AWS events.

AWS Summits season is starting! I’m already working with the local team to prepare content for the Summits in Paris and London. Summits are free online and in-person events that bring the cloud computing community together to connect, collaborate, and learn about AWS. Stay updated by visiting the official AWS Summit website and sign up for notifications to learn when registration opens for events in your area.

AWS GenAI Lofts are collaborative spaces and immersive experiences that showcase AWS expertise in cloud computing and AI. They provide startups and developers with hands-on access to AI products and services, exclusive sessions with industry leaders, and valuable networking opportunities with investors and peers. Find a GenAI Loft location near you, and don’t forget to register.

Browse all upcoming AWS led in-person and virtual events here.

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

— seb

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

AWS Weekly Roundup: New Asia Pacific Region, DynamoDB updates, Amazon Q developer, and more (January 13, 2025)

Post Syndicated from Betty Zheng (郑予彬) original https://aws.amazon.com/blogs/aws/aws-weekly-roundup-new-asia-pacific-region-dynamodb-updates-amazon-q-developer-and-more-january-13-2025/

As we move into the second week of 2025, China is celebrating Laba Festival (腊八节), a traditional holiday, which marks the beginning of Chinese New Year preparations. On this day, Chinese people prepare Laba congee, a special porridge combining various grains, dried fruits, and nuts. This

nutritious mixture symbolizes harmony, prosperity, and good fortune — with each ingredient representing the diversity and abundance of life. This traditional practice dates back to when Buddha achieved enlightenment after consuming rice porridge, making it a symbol of both material and spiritual nourishment. The festival, occurring on the eighth day of the twelfth lunar month, marks the countdown to Spring Festival, China’s most significant traditional holiday celebrating family reunion and renewal.

As our global tech community grows, such cultural celebrations remind us of the importance of inclusive innovation and shared progress.

Last week’s launches

Let’s take a look at what Amazon Web Services (AWS) launched in this week.

New AWS Asia Pacific (Thailand) Region– AWS has expanded its global infrastructure with the launch of the new Asia Pacific (Thailand) AWS Region, featuring three Availability Zones. With this addition, customers in Thailand and throughout Southeast Asia can serve customers with reduced latency while maintaining data residency within Thailand. The newly launched Region supports the complete range of AWS services and strengthens our presence in the rapidly growing ASEAN market.

New AWS Direct Connect location in Bangkok – Following the launch of our Thailand Region, we’ve established a new AWS Direct Connect location in Bangkok and expanded our existing infrastructure. This addition provides customers in Thailand with improved connectivity options and reduced network latency when accessing AWS services.

Database and analytics

Configurable point-in-time recovery periods for Amazon DynamoDB – Amazon DynamoDB now enables customizable point-in-time recovery (PITR) periods, which means customers can specify recovery durations ranging from 1 to 35 days on a per-table basis. This enhancement enables organizations to meet precise compliance requirements while maximizing cost-efficiency. The feature is now available across all AWS Regions, including AWS GovCloud (US West) and China Regions. This flexibility in data recovery periods empowers customers to align their backup policies precisely with their business requirements and regulatory obligations.

Amazon MSK Connect APIs with AWS PrivateLink – Amazon Managed Streaming for Apache Kafka Connect (Amazon MSK Connect) APIs now support AWS PrivateLink, giving customers access to MSK Connect APIs through private endpoints within their virtual private cloud (VPC). This enhancement provides increased security and reduced data exposure by keeping traffic within the AWS network.

Generative AI and machine learning

Amazon Q Developer in SageMaker Code Editor– Amazon Q Developer is now integrated into the Amazon SageMaker Code Editor integrated development environment (IDE), enhancing the developer’s experience with AI-powered code assistance. Intelligent code suggestions, documentation assistance, and contextual recommendations are now directly available within the SageMaker development environment.

Management and governance

AWS Systems Manager Automation in AWS Chatbot – AWS Chatbot now offers 20 additional AWS Systems Manager Automation runbook recommendations, expanding its capabilities for automated operations management. These new recommendations help customers streamline their operational tasks and implement best practices more efficiently through chat-based interactions.

AWS Transit Gateway cost analysis enhancement – We’ve introduced new capabilities for analyzing Transit Gateway data processing charges using cost allocation tags. This feature provides improved visibility and control over networking costs, enabling organizations to track and optimize AWS Transit Gateway usage efficiently. The enhanced cost analysis tools deliver detailed insights into network traffic patterns and associated costs.

Other AWS news and highlights

2024’s most popular DevOps blog posts – The retrospective blog post “The most visited DevOps and Developer Productivity blog posts in 2024” has reached the top one position on this week’s AWS most popular articles chart. This compilation presents the most influential DevOps content from 2024, offering insights into trending topics and best practices. The collection examines key developments in continuous integration and continuous development (CI/CD), infrastructure as code (IaC), and automation practices.

New security course for generative AI – AWS Skill Builder has released a new course focusing on securing generative AI applications on AWS. This comprehensive training teaches professionals to implement security best practices for artificial intelligence and machine learning (AI/ML) workloads, addressing data protection, model security, and compliance requirements. The course meets the growing demand for specialized security knowledge in the rapidly evolving field of generative AI.

Amazon Connect Contact Lens free trials – We’re introducing free trials for first-time users of Amazon Connect Contact Lens conversational analytics and performance evaluations. New customers can process up to 100,000 voice minutes monthly at no cost for 2 months, and first-time performance evaluation users receive a 30-day free trial starting with their first evaluation. With this initiative, customers can experience Contact Lens capabilities in their environment without additional costs. The free trials are available across all AWS Regions where Contact Lens is supported.

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

Whether you’re a developer, architect, business leader, or you’re starting your cloud journey – and regardless of what 2024 brought your way – 2025 presents new opportunities for everyone.

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

– Betty

Newly enhanced Amazon Connect adds generative AI, WhatsApp Business, and secure data collection

Post Syndicated from Elizabeth Fuentes original https://aws.amazon.com/blogs/aws/newly-enhanced-amazon-connect-adds-generative-ai-whatsapp-business-and-secure-data-collection/

Today, Amazon Connect introduces a set of new features that help businesses enhance their contact center operations through generative AI, advanced security features, and streamlined bot management. These innovations help businesses deliver better customer experiences by creating more time and space for meaningful human interactions, while maintaining security and compliance.

Contact center managers continually face challenges in optimizing self-service resolution rates, evaluating agent performance efficiently, and maintaining data privacy compliance. Additionally, creating and managing conversational AI experiences often requires specialized expertise and complex integrations across multiple services.

To address these challenges, Amazon Connect introduced key features such as generative AI–powered customer segmentation for targeted campaigns, native WhatsApp Business messaging for omnichannel support, secure collection of sensitive customer data in chat interactions, simplified conversational AI bot management in the Amazon Connect interface, and new enhancements to Amazon Q in Connect. Amazon Connect also added new analytics capabilities through Amazon Connect Contact Lens to help optimize bot performance and contact center operations.

Here are the new capabilities that will help you create more personalized and efficient customer experiences while maintaining the highest standards of data security and operational excellence.

Generative AI powered features
Amazon Connect integrates new generative AI capabilities to automate and enhance customer interactions, enabling smarter targeting and more efficient contact center management.

Generative AI segmentation and trigger-based campaigns – Uses generative AI–powered assistance to create customer segments using conversational prompts. This allows businesses to create precise customer segments using natural language descriptions, making it easier to identify and reach specific customer groups. Trigger campaigns enable organizations to communicate with their customers based on specific customer events, such as cart abandonment.

You can also start with ready-to-use suggestions.

Simplify conversational AI bot creation and enhance them with Amazon Q in Connect – Create, edit, and manage conversational AI bots powered by Amazon Lex directly within the Amazon Connect web interface. You can now enhance these bots with Amazon Q in Connect, a generative AI–powered assistant for customer service. Amazon Q in Connect now supports end-customer self-service interactions across interactive voice response (IVR) and digital channels, in addition to assisting contact center agents with recommended responses and actions.

This integration extends beyond traditional voice and chatbot Amazon Lex capabilities by providing advanced conversational abilities via large language models (LLMs). The system intelligently searches configured knowledge bases, customer information, web content, and third-party application data to respond to customer questions when they don’t match predefined intents. Administrators can set custom guardrails for their instance, defining restrictions on response generation and monitoring Amazon Q in Connect performance.

Generative AI–powered automated evaluations: Supervisors can automatically evaluate up to 100 percent of contacts using generative AI.

Generative AI–powered contact categorization: Improves existing semantic match functionality using natural language intents.

Improved interfaces and tools
Enhanced capabilities for bot management and monitoring, simplifying the creation and optimization of automated experiences.

Amazon Connect for WhatsApp Business messaging – Natively integrate with WhatsApp Business messaging so customers can receive support over WhatsApp in addition to existing Amazon Connect channels such as voice, SMS, chat, and Apple Messages for Business. This addition to Amazon Connect omnichannel capabilities helps businesses meet customers on their preferred communication channel while maintaining consistent service delivery and management within the Amazon Connect application.

Contact Lens conversational AI bot dashboards – Offers analytics to monitor the performance of your conversational AI bots built in Amazon Connect.

Self-service voice (IVR) recording and interaction logs on contact details – Provides comprehensive records of self-service interactions, including audio recordings.

Improved intraday forecasts – Allows comparison of intraday forecasts against previously published forecasts.

Salesforce Contact Center with Amazon Connect (Preview) – Natively integrates the digital channels and unified routing of Amazon Connect into Salesforce customer relationship management (CRM) system. This new offering allows companies to use a single routing and workflow system for both Amazon Connect and Salesforce channels, intelligently directing calls, chats, and cases to the appropriate self-service or agent interaction. If you’re interested, sign up to join the preview.

Enhanced security for chat
New features that enhance security and compliance in chat interactions, enabling secure handling of sensitive information.

Collection of sensitive customer data within chats – Amazon Connect chat and messaging now includes a data privacy option that enables secure handling of sensitive customer information during chat interactions. This feature protects personally identifiable information (PII) and payment card industry (PCI) data, promoting compliance with data protection regulations.

Key benefits
The latest features of Amazon Connect combine generative AI, enhanced security, and streamlined bot management to help businesses:

Transform customer experience – Amazon Connect elevates customer interactions through AI–powered segmentation, enabling personalized engagement strategies. The new WhatsApp Business messaging expands omnichannel support capabilities, meeting customers on their preferred channel. Additionally, advanced bot capabilities, including Amazon Q in Connect, enhance self-service resolution rates, delivering more efficient customer experiences.

Enhance security and operations – Contact centers can now strengthen their security posture with PCI-compliant chat interactions while maintaining operational efficiency. Custom AI guardrails promote appropriate response generation, while the simplified bot management interface eliminates the need for specialized expertise. Analytics and forecasting capabilities provide comprehensive performance monitoring, enabling data-driven decision-making for optimal contact center operations.

Pricing and availability – These features are available today in all AWS Regions where Amazon Connect is supported. For pricing, visit the Amazon Connect Pricing. For implementation guidance, visit the Amazon Connect documentation.

— Eli

Channel deflection from voice to chat using Amazon Connect

Post Syndicated from Siva Thangavel original https://aws.amazon.com/blogs/architecture/channel-deflection-from-voice-to-chat-using-amazon-connect/

This post was co-written with Sagar Bedmutha, senior solutions architect at Tata Consultancy Services, and Rajiya Patan, AWS developer at Tata Consultancy Services

Service excellence helps cultivate customer satisfaction and brand loyalty. According to Gartner, one service excellence challenge is long wait times on interactive voice response (IVR) systems. Long wait times can translate into frustrated customers and potentially lost business. To maintain and grow business, companies must examine the shape of their customer service—avoiding long wait times, offering alternative communication channels such as chat, and designing easier-to-use, more efficient systems.

Amazon Connect, an AWS cloud-based contact center solution, is specialized in both voice and chat communication. This powerful tool can open up new avenues for businesses to enhance their customer service experience. Through Amazon Connect, companies can implement strategies like transferring a voice call to a chat channel. This can help resolve the pain point of wait times while maintaining the continuity of the engagement with customers.

This post outlines an Amazon Connect architecture pattern for transitioning between voice and chat channels. With this solution, a customer in a long queue on a voice call can choose a callback or to continue the conversation with an agent through chat.

Prerequisites

To implement this solution, you’ll need the following:

Solution overview

Our solution provides an alternate channel and call-back option if there is a long wait time in IVR. Customers can transition from voice to a chat or email instantly without additional work.

We designed this solution by using the following AWS services and custom widget:

  •  Amazon Connect – Omnichannel cloud contact center that helps you provide superior customer service at a lower cost. Amazon Connect contact flows define the customer experience from start to finish.
  •  Lambda – Serverless, event-driven compute service that lets you run code for virtually any type of application or backend service, without you needing to provision or manage servers.
  •  CloudFront – Content delivery network (CDN) that speeds up delivery of static and dynamic web content, such as HTML, CSS, JavaScript, and images. CloudFront caches content at edge locations closer to end users.
  •  Amazon Pinpoint – Flexible, scalable marketing communications service that connects you with customers over email, SMS, push notifications, or voice.
  •  Customized chat widget – Hosted in an Amazon S3 bucket, the widget provides the interface for chat interactions. It is developed using HTML, Vanilla JavaScript, and customized styling.

The following high-level architecture diagram outlines the flow of the process.

Architecture diagram showing the flow from the customer call to chatting with a live agent. Detailed description follows in text.

Channel deflection architecture diagram

  1. The customer initiates a call to the IVR system for customer support.
  2. If there is a long wait time, the IVR system provides an option for callback through the voice channel or the ability to switch to another channel like chat or SMS.
  3. The customer selects option to transition the call to a chat channel.
  4. The Amazon Connect flow invokes a Lambda function to create a chat session for the customer. The Lambda function generates a secure, time-limited signed URL for the chat channel, including relevant context.
  5. The solution sends the URL to the customer’s registered mobile number and email address through Amazon Pinpoint.
  6. The customer receives the chat link on their mobile device or email, then they select the link.
  7. A chat session initiates in a web browser, and a live agent is connected to assist the customer.

Note: The chat link becomes inactive if the user doesn’t access it within the designated schedule.

Implementation considerations

When implementing this voice-to-chat transition solution, it’s important to consider the following:

  • Ensure that your AWS account has the necessary permissions, and that you’ve set up appropriate IAM roles and policies for secure access to Amazon Connect, Lambda, Amazon S3, CloudFront, and Amazon Pinpoint.
  • Ensure that you have the necessary technical knowledge. Familiarity with Amazon Connect contact flows is crucial, as is proficiency in developing and deploying Lambda functions. You must create custom Lambda functions to handle the chat session creation and generate secure, time-limited signed URLs.
  • Set up an S3 bucket to host your custom chat widget, and configure a CloudFront distribution for performance and security.
  • Integrate Amazon Pinpoint for communication delivery. This requires careful setup to handle email and SMS notifications effectively.
  • When developing the custom chat widget, focus on creating a user-friendly interface that integrates with the Amazon Connect chat API. Pay special attention to security measures, particularly in generating and managing the signed URLs for chat access.
  • Complete testing to confirm smooth operations across various scenarios, including edge cases like expired chat links.
  • Remember to monitor the solution’s performance in production and consider scalability as your customer base grows.

By addressing these implementation considerations, you’ll be well-positioned to deploy a robust and effective voice-to-chat transition system that enhances your customer service capabilities.

Extended use cases

You can extend this solution for solving other contact center use cases with minimal or no modification. The following are some examples:

  • Assisting customers with complex technical issues that require a step by step guide.
  • Helping customers to follow instructions by reading the manual to complete backend processes, like profile updates.
  • Overcoming language barriers with international customer support by using writing instead of voice.
  • Authenticating customers using address, zip code, or other demographics.
  • Offering chat functionality to customers who prefer to multitask during interactions.
  • Deflecting traffic to alternate channels to improve customer experience and reduce costs.
  • Offering a method for secure document exchange, such as during financial services consultations.

Conclusion

Using Amazon Connect and other AWS services, this solution offers an implementation that can transition voice calls to a chat channel. This approach provides flexibility to your customer so that they can switch between channels. This helps to improve the total customer experience, the company’s efficiency, and the agent’s productivity. The flow provides continuity in conversations, so that agents can resume conversations with clients across channels and still maintain context. In the end, this solution empowers companies to deliver exceptional customer service and drive positive outcomes for their business. You can learn more about using Amazon Connect by visiting our Amazon Connect Resources page.

AWS Weekly Roundup: Amazon EC2 U7i Instances, Bedrock Converse API, AWS World IPv6 Day and more (June 3, 2024)

Post Syndicated from Channy Yun original https://aws.amazon.com/blogs/aws/aws-weekly-roundup-amazon-ec2-u7i-instances-bedrock-converse-api-aws-world-ipv6-day-and-more-june-3-2024/

Life is not always happy, there are difficult times. However, we can share our joys and sufferings with those we work with. The AWS Community is no exception.

Jeff Barr introduced two members of the AWS community who are dealing with health issues. Farouq Mousa is an AWS Community Builder and fighting brain cancer. Allen Helton is an AWS Serverless Hero and his young daughter is fighting leukemia.

Please donate to support Farauq and Olivia, Allen’s daughter to overcome their disease.

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

Amazon EC2 high memory U7i Instances – These instances with up to 32 TiB of DDR5 memory and 896 vCPUs are powered by custom fourth generation Intel Xeon Scalable Processors (Sapphire Rapids). These high memory instances are designed to support large, in-memory databases including SAP HANA, Oracle, and SQL Server. To learn more, visit Jeff’s blog post.

New Amazon Connect analytics data lake – You can use a single source for contact center data including contact records, agent performance, Contact Lens insights, and more — eliminating the need to build and maintain complex data pipelines. Your organization can create your own custom reports using Amazon Connect data or combine data queried from third-party sources. To learn more, visit Donnie’s blog post.

Amazon Bedrock Converse API – This API provides developers a consistent way to invoke Amazon Bedrock models removing the complexity to adjust for model-specific differences such as inference parameters. With this API, you can write a code once and use it seamlessly with different models in Amazon Bedrock. To learn more, visit Dennis’s blog post to get started.

New Document widget for PartyRock – You can build, use, and share generative AI-powered apps for fun and for boosting personal productivity, using PartyRock. Its widgets display content, accept input, connect with other widgets, and generate outputs like text, images, and chats using foundation models. You can now use new document widget to integrate text content from files and documents directly into a PartyRock app.

30 days of alarm history in Amazon CloudWatch – You can view the history of your alarm state changes for up to 30 days prior. Previously, CloudWatch provided 2 weeks of alarm history. This extended history makes it easier to observe past behavior and review incidents over a longer period of time. To learn more, visit the CloudWatch alarms documentation section.

10x faster startup time in Amazon SageMaker Canvas – You can launch SageMaker Canvas in less than a minute and get started with your visual, no-code interface for machine learning 10x faster than before. Now, all new user profiles created in existing or new SageMaker domains can experience this accelerated startup time.

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

Other AWS news
Here are some additional news items and a Twitch show that you might find interesting:

Let us manage your relational database! – Jeff Barr ran a poll to better understand why some AWS customers still choose to host their own databases in the cloud. Working backwards, he highlights four issues that AWS managed database services address. Consider these before hosting your own database.

Amazon Bedrock Serverless Prompt Chaining – This repository provides examples of using AWS Step Functions and Amazon Bedrock to build complex, serverless, and highly scalable generative AI applications with prompt chaining.

AWS Merch Store Spring Sale – Do you want to buy AWS branded t-shirts, hats, bags, and so on? Get 15% off on all items now through June 7th.

Upcoming AWS events
Check your calendars and sign up for these AWS events:

AWS World IPv6 Day — Join us a free in-person celebration event on June 6, for technical presentations from AWS experts plus a workshop and whiteboarding session. You will learn how to get started with IPv6 and hear from customers who have started on the journey of IPv6 adoption. Check out your near city: San Francisco, Seattle, New York,  London, Mumbai, Bangkok, Singapore, Kuala Lumpur, Beijing, Manila, and Sydney.

AWS Summits — Join free online and in-person events that bring the cloud computing community together to connect, collaborate, and learn about AWS. Register in your nearest city: Stockholm (June 4), Madrid (June 5), and Washington, DC (June 26–27).

AWS re:Inforce — Join us for AWS re:Inforce (June 10–12) in Philadelphia, PA. AWS re:Inforce is a learning conference focused on AWS security solutions, cloud security, compliance, and identity. Connect with the AWS teams that build the security tools and meet AWS customers to learn about their security journeys.

AWS Community Days — Join community-led conferences that feature technical discussions, workshops, and hands-on labs led by expert AWS users and industry leaders from around the world: Midwest | Columbus (June 13), Sri Lanka (June 27), Cameroon (July 13), New Zealand (August 15), Nigeria (August 24), and New York (August 28).

You can browse all upcoming in-person and virtual events.

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

— Channy

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

Simplify custom contact center insights with Amazon Connect analytics data lake

Post Syndicated from Donnie Prakoso original https://aws.amazon.com/blogs/aws/simplify-custom-contact-center-insights-with-amazon-connect-analytics-data-lake/

Analytics are vital to the success of a contact center. Having insights into each touchpoint of the customer experience allows you to accurately measure performance and adapt to shifting business demands. While you can find common metrics in the Amazon Connect console, sometimes you need to have more details and custom requirements for reporting based on the unique needs of your business. 

Starting today, the Amazon Connect analytics data lake is generally available. As announced last year as preview, this new capability helps you to eliminate the need to build and maintain complex data pipelines. Amazon Connect data lake is zero-ETL capable, so no extract, transform, or load (ETL) is needed.

Here’s a quick look at the Amazon Connect analytics data lake:

Improving your customer experience with Amazon Connect
Amazon Connect analytics data lake helps you to unify disparate data sources, including customer contact records and agent activity, into a single location. By having your data in a centralized location, you now have access to analyze contact center performance and gain insights while reducing the costs associated with implementing complex data pipelines.

With Amazon Connect analytics data lake, you can access and analyze contact center data, such as contact trace records and Amazon Connect Contact Lens data. This provides you the flexibility to prepare and analyze data with Amazon Athena and use the business intelligence (BI) tools of your choice, such as, Amazon QuickSight and Tableau. 

Get started with the Amazon Connect analytics data lake
To get started with the Amazon Connect analytics data lake, you’ll first need to have an Amazon Connect instance setup. You can follow the steps in the Create an Amazon Connect instance page to create a new Amazon Connect instance. Because I’ve already created my Amazon Connect instance, I will go straight to showing you how you can get started with Amazon Connect analytics data lake.

First, I navigate to the Amazon Connect console and select my instance.

Then, on the next page, I can set up my analytics data lake by navigating to Analytics tools and selecting Add data share.

This brings up a pop-up dialog, and I first need to define the target AWS account ID. With this option, I can set up a centralized account to receive all data from Amazon Connect instances running in multiple accounts. Then, under Data types, I can select the types I need to share with the target AWS account. To learn more about the data types that you can share in the Amazon Connect analytics data lake, please visit Associate tables for Analytics data lake.

Once it’s done, I can see the list of all the target AWS account IDs with which I have shared all the data types.

Besides using the AWS Management Console, I can also use the AWS Command Line Interface (AWS CLI) to associate my tables with the analytics data lake. The following is a sample command:

$> aws connect batch-associate-analytics-data-set --cli-input-json file:///input_batch_association.json

Where input_batch_association.json is a JSON file that contains association details. Here’s a sample:

{
	"InstanceId": YOUR_INSTANCE_ID,
	"DataSetIds": [
		"<DATA_SET_ID>"
		],
	"TargetAccountId": YOUR_ACCOUNT_ID
}

Next, I need to approve (or reject) the request in the AWS Resource Access Manager (RAM) console in the target account. RAM is a service to help you securely share resources across AWS accounts. I navigate to AWS RAM and select Resource shares in the Shared with me section.

Then, I select the resource and select Accept resource share. 

At this stage, I can access shared resources from Amazon Connect. Now, I can start creating linked tables from shared tables in AWS Lake Formation. In the Lake Formation console, I navigate to the Tables page and select Create table.

I need to create a Resource link to a shared table. Then, I fill in the details and select the available Database and the Shared table’s region.

Then, when I select Shared table, it will list all the available shared tables that I can access.

Once I select the shared table, it will automatically populate Shared table’s database and Shared table’s owner ID. Once I’m happy with the configuration, I select Create.

To run some queries for the data, I go to the Amazon Athena console.The following is an example of a query that I ran:

With this configuration, I have access to certain Amazon Connect data types. I can even visualize the data by integrating with Amazon QuickSight. The following screenshot show some visuals in the Amazon QuickSight dashboard with data from Amazon Connect.

Customer voice
During the preview period, we heard lots of feedback from our customers about Amazon Connect analytics data lake. Here’s what our customer say:

Joulica is an analytics platform supporting insights for software like Amazon Connect and Salesforce. Tony McCormack, founder and CEO of Joulica, said, “Our core business is providing real-time and historical contact center analytics to Amazon Connect customers of all sizes. In the past, we frequently had to set up complex data pipelines, and so we are excited about using Amazon Connect analytics data lake to simplify the process of delivering actionable intelligence to our shared customers.”

Things you need to know

  • Pricing — Amazon Connect analytics data lake is available for you to use up to 2 years of data without any additional charges in Amazon Connect. You only need to pay for any services you use to interact with the data.
  • Availability — Amazon Connect analytics data lake is generally available in the following AWS Regions: US East (N. Virginia), US West (Oregon), Africa (Cape Town), Asia Pacific (Mumbai, Seoul, Singapore, Sydney, Tokyo), Canada (Central), and Europe (Frankfurt, London)
  • Learn more — For more information, please visit Analytics data lake documentation page.

Happy building,
— Donnie

New generative AI features in Amazon Connect, including Amazon Q, facilitate improved contact center service

Post Syndicated from Veliswa Boya original https://aws.amazon.com/blogs/aws/new-generative-ai-features-in-amazon-connect-including-amazon-q-facilitate-improved-contact-center-service/

If you manage a contact center, then you know the critical role that agents play in helping your organization build customer trust and loyalty. Those of us who’ve reached out to a contact center know how important agents are with guiding through complex decisions and providing fast and accurate solutions where needed. This can take time, and if not done correctly, then it may lead to frustration.

Generative AI capabilities in Amazon Connect
Today, we’re announcing that the existing artificial intelligence (AI) features of Amazon Connect now have generative AI capabilities that are powered by large language models (LLMs) available through Amazon Bedrock to transform how contact centers provide service to customers. LLMs are pre-trained on vast amounts of data, commonly known as foundation models (FMs), and they can understand and learn, generate text, engage in interactive conversations, answer questions, summarize dialogs and documents, and provide recommendations.

Amazon Q in Connect: recommended responses and actions for faster customer support
Organizations are in a state of constant change. To maintain a high level of performance that keeps up with these organizational changes, contact centers continuously onboard, train, and coach agents. Even with training and coaching, agents must often search through different sources of information, such as product guides and organization policies, to provide exceptional service to customers. This can increase customer wait times, lowering customer satisfaction and increasing contact center costs.

Amazon Q in Connect, a generative AI-powered agent assistant that includes functionality formerly available as Amazon Connect Wisdom, understands customer intents and uses relevant sources of information to deliver accurate responses and actions for the agent to communicate and resolve unique customer needs, all in real-time. Try Amazon Q in Connect for no charge until March 1, 2024. The feature is easy to enable, and you can get started in the Amazon Connect console.

Amazon Connect Contact Lens: generative post-contact summarization for increased productivity
To improve customer interactions and make sure details are available for future reference, contact center managers rely on the notes that agents manually create after every customer interaction. These notes include details on how a customer issue was addressed, key moments of the conversation, and any pending follow-up items.

Amazon Connect Contact Lens now provides generative AI-powered post-contact summarization, and enables contact center managers to more efficiently monitor and help improve contact quality and agent performance. For example, you can use summaries to track commitments made to customers and make sure of the prompt completion of follow-up actions. Moments after a customer interaction, Contact Lens now condenses the conversation into a concise and coherent summary.

Amazon Lex in Amazon Connect: assisted slot resolution
Using Amazon Lex, you can already build chatbots, virtual agents, and interactive voice response (IVR) which lets your customers schedule an appointment without speaking to a human agent. For example, “I need to change my travel reservation for myself and my two children,” might be difficult for a traditional bot to resolve to a numeric value (how many people are on the travel reservation?).

With the new assisted slot resolution feature, Amazon Lex can now resolve slot values in user utterances with great accuracy (for example, providing an answer to the previous question by providing a correct numeric value of three). This is powered by the advanced reasoning capabilities of LLMs which improve accuracy and provide a better customer experience. Learn about all the features of Amazon Lex, including the new generative AI-powered capabilities to help you build better self-service experiences.

Amazon Connect Customer Profiles: quicker creation of unified customer profiles for personalized customer experiences
Customers expect personalized customer service experiences. To provide this, contact centers need a comprehensive understanding of customers’ preferences, purchases, and interactions. To achieve that, contact center administrators create unified customer profiles by merging customer data from a number of applications. These applications each have different types of customer data stored in varied formats across a range of data stores. Stitching together data from these various data stores needs contact center administrators to understand their data and figure out how to organize and combine it into a unified format. To accomplish this, they spend weeks compiling unified customer profiles.

Starting today, Amazon Connect Customer Profiles uses LLMs to shorten the time needed to create unified customer profiles. When contact center administrators add data sources such as Amazon Simple Storage Service (Amazon S3), Adobe Analytics, Salesforce, ServiceNow, and Zendesk, Customer Profiles analyze the data to understand what the data format and content represents and how the data relates to customers’ profiles. Then, Customer Profiles then automatically determines how to organize and combine data from different sources into complete, accurate profiles. With just a few steps, managers can review, make any necessary edits, and complete the setup of customer profiles.

Review summary mapping

In-app, web, and video capabilities in Amazon Connect
As an organization, you want to provide great, easy-to-use, and convenient customer service. Earlier in this post I talked about self-service chatbots and how they help you with this. At times customers want to move beyond the chatbot, and beyond an audio conversation with the agent.

Amazon Connect now has in-app, web, and video capabilities to help you deliver rich, personalized customer experiences (see Amazon Lex features for details). Using the fully-managed communication widget, and with a few lines of code, you can implement these capabilities on your web and mobile applications. This allows your customers to get support from a web or mobile application without ever having to leave the page. Video can be enabled by either the agent only, by the customer only, or by both agent and customer.

Video calling

Amazon Connect SMS: two-way SMS capabilities
Almost everyone owns a mobile device and we love the flexibility of receiving text-based support on-the-go. Contact center leaders know this, and in the past have relied on disconnected, third-party solutions to provide two-way SMS to customers.

Amazon Connect now has two-way SMS capabilities to enable contact center leaders to provide this flexibility (see Amazon Lex features for details). This improves customer satisfaction and increases agent productivity without costly integration with third-party solutions. SMS chat can be enabled using the same configuration, Amazon Connect agent workspace, and analytics as calls and chats.

Learn more

Send feedback

– Veliswa

AWS Weekly Roundup – EC2 DL2q instances, PartyRock, Amplify’s 6th birthday, and more – November 20, 2023

Post Syndicated from Channy Yun original https://aws.amazon.com/blogs/aws/aws-weekly-roundup-ec2-dl2q-instances-partyrock-amplifys-6th-birthday-and-more-november-20-2023/

Last week I saw an astonishing 160+ new service launches. There were so many updates that we decided to publish a weekly roundup again. This continues the same innovative pace of the previous week as we are getting closer to AWS re:Invent 2023.

Our News Blog team is also finalizing new blog posts for re:Invent to introduce awesome launches with service teams for your reading pleasure. Jeff Barr shared The Road to AWS re:Invent 2023 to explain our blogging journey and process. Please stay tuned in the next week!

Last week’s launches
Here are some of the launches that caught my attention last week:

Amazon EC2 DL2q instances – New DL2q instances are powered by Qualcomm AI 100 Standard accelerators and are the first to feature Qualcomm’s AI technology in the public cloud. With eight Qualcomm AI 100 Standard accelerators and 128 GiB of total accelerator memory, you can run popular generative artificial intelligence (AI) applications and extend to edge devices across smartphones, autonomous driving, personal compute, and extended reality headsets to develop and validate these AI workloads before deploying.

PartyRock for Amazon Bedrock – We introduced PartyRock, a fun and intuitive hands-on, generative AI app-building playground powered by Amazon Bedrock. You can experiment, learn all about prompt engineering, build mini-apps, and share them with your friends—all without writing any code or creating an AWS account.

You also can now access the Meta Llama 2 Chat 13B foundation model and Cohere Command Light, Embed English, and multilingual models for Amazon Bedrock.

AWS Amplify celebrates its sixth birthday – We announced six new launches; a new documentation site, support for Next.js 14 with our hosting and JavaScript library, added custom token providers and an automatic React Native social sign-in update to Amplify Auth, new ChangePassword and DeleteUser account settings components, and updated all Amplify UI packages to use new Amplify JavaScript v6. You can also use wildcard subdomains when using a custom domain with your Amplify application deployed to AWS Amplify Hosting.

Amplify docs site UI

Also check out other News Blog posts about major launches published in the past week:

Other AWS service launches
Here are some other bundled feature launches per AWS service:

Amazon Athena  – You can use a new cost-based optimizer (CBO) to enhance query performance based on table and column statistics, collected by AWS Glue Data Catalog and Athena JDBC 3.x driver, a new alternative that supports almost all authentication plugins. You can also use Amazon EMR Studio to develop and run interactive queries on Amazon Athena.

Amazon CloudWatch – You can use a new CloudWatch metric called EBS Stalled I/O Check to monitor the health of your Amazon EBS volumes, the regular expression for Amazon CloudWatch Logs Live Tail filter pattern syntax to search and match relevant log events, observability of SAP Sybase ASE database in CloudWatch Application Insights, and up to two stats commands in a Log Insights query to perform aggregations on the results.

Amazon CodeCatalyst – You can connect to a Amazon Virtual Private Cloud (Amazon VPC) from CodeCatalyst Workflows, provision infrastructure using Terraform within CodeCatalyst Workflows, access CodeCatalyst with your workforce identities configured in IAM Identity Center, and create teams made up of members of the CodeCatalyst space.

Amazon Connect – You can use a pre-built queue performance dashboard and Contact Lens conversational analytics dashboard to view and compare real-time and historical aggregated queue performance. You can use quick responses for chats, previously written formats such as typing in ‘/#greet’ to insert a personalized response, and scanning attachments to detect malware or other unwanted content.

AWS Glue – AWS Glue for Apache Spark added new six database connectors: Teradata, SAP HANA, Azure SQL, Azure Cosmos DB, Vertica, and MongoDB, as well as the native connectivity to Amazon OpenSearch Service.

AWS Lambda – You can see single pane view of metrics, logs, and traces in the AWS Lambda console and advanced logging controls to natively capture logs in JSON structured format. You can view the SAM template on the Lambda console and export the function’s configuration to AWS Application Composer. AWS Lambda also supports Java 21 and NodeJS 20 versions built on the new Amazon Linux 2023 runtime.

AWS Local Zones in Dallas – You can enable the new Local Zone in Dallas, Texas, us-east-1-dfw-2a, with Amazon EC2 C6i, M6i, R6i, C6gn, and M6g instances and Amazon EBS volume types gp2, gp3, io1, sc1, and st1. You can also access Amazon ECS, Amazon EKS, Application Load Balancer, and AWS Direct Connect in this new Local Zone to support a broad set of workloads at the edge.

Amazon Managed Streaming for Apache Kafka (Amazon MSK) – You can standardize access control to Kafka resources using AWS Identity and Access Management (IAM) and build Kafka clients for Amazon MSK Serverless written in all programming languages. These are open source client helper libraries and code samples for popular languages, including Java, Python, Go, and JavaScript. Also, Amazon MSK now supports an enhanced version of Apache Kafka 3.6.0 that offers generally available Tiered Storage and automatically sends you storage capacity alerts when you are at risk of exhausting your storage.

Amazon OpenSearch Service Ingestion – You can migrate your data from Elasticsearch version 7.x clusters to the latest versions of Amazon OpenSearch Service and use persistent buffering to protect the durability of incoming data.

Amazon RDS –Amazon RDS for MySQL now supports creating active-active clusters using the Group Replication plugin, upgrading MySQL 5.7 snapshots to MySQL 8.0, and Innovation Release version of MySQL 8.1.

Amazon RDS Custom for SQL Server extends point-in-time recovery support for up to 1,000 databases, supports Service Master Key Retention to use transparent data encryption (TDE), table- and column-level encryption, DBMail and linked servers, and use SQL Server Developer edition with the bring your own media (BYOM).

Additionally, Amazon RDS Multi-AZ deployments with two readable standbys now supports minor version upgrades and system maintenance updates with typically less than one second of downtime when using Amazon RDS Proxy.

AWS Partner Central – You can use an improved user experience in AWS Partner Central to build and promote your offerings and the new Investments tab in the Partner Analytics Dashboard to gain actionable insights. You can now link accounts and associated users between Partner Central and AWS Marketplace and use an enhanced co-sell experience with APN Customer Engagements (ACE) manager.

Amazon QuickSight – You can programmatically manage user access and custom permissions support for roles to restrict QuickSight functionality to the QuickSight account for IAM Identity Center and Active Directory using APIs. You can also use shared restricted folders, a Contributor role and support for data source asset types in folders and the Custom Week Start feature, an addition designed to enhance the data analysis experience for customers across diverse industries and social contexts.

AWS Trusted Advisor – You can use new APIs to programmatically access Trusted Advisor best practices checks, recommendations, and prioritized recommendations and 37 new Amazon RDS checks that provide best practices guidance by analyzing DB instance configuration, usage, and performance data.

There’s a lot more launch news that I haven’t covered. See AWS What’s New for more details.

See you virtually in AWS re:Invent
AWS re:Invent 2023Next week we’ll hear the latest from AWS, learn from experts, and connect with the global cloud community in Las Vegas. If you come, check out the agenda, session catalog, and attendee guides before your departure.

If you’re not able to attend re:Invent in person this year, we’re offering the option to livestream our Keynotes and Innovation Talks. With the registration for online pass, you will have access to on-demand keynote, Innovation Talks, and selected breakout sessions after the event.

– Channy

AWS Weekly Roundup – Amazon MWAA, EMR Studio, Generative AI, and More – August 14, 2023

Post Syndicated from Antje Barth original https://aws.amazon.com/blogs/aws/aws-weekly-roundup-amazon-mwaa-emr-studio-generative-ai-and-more-august-14-2023/

While I enjoyed a few days off in California to get a dose of vitamin sea, a lot has happened in the AWS universe. Let’s take a look together!

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

Amazon MWAA now supports Apache Airflow version 2.6 – Amazon Managed Workflows for Apache Airflow (Amazon MWAA) is a managed orchestration service for Apache Airflow that you can use to set up and operate end-to-end data pipelines in the cloud. Apache Airflow version 2.6 introduces important security updates and bug fixes that enhance the security and reliability of your workflows. If you’re currently running Apache Airflow version 2.x, you can now seamlessly upgrade to version 2.6.3. Check out this AWS Big Data Blog post to learn more.

Amazon EMR Studio adds support for AWS Lake Formation fine-grained access control – Amazon EMR Studio is a web-based integrated development environment (IDE) for fully managed Jupyter notebooks that run on Amazon EMR clusters. When you connect to EMR clusters from EMR Studio workspaces, you can now choose the AWS Identity and Access Management (IAM) role that you want to connect with. Apache Spark interactive notebooks will access only the data and resources permitted by policies attached to this runtime IAM role. When data is accessed from data lakes managed with AWS Lake Formation, you can enforce table and column-level access using policies attached to this runtime role. For more details, have a look at the Amazon EMR documentation.

AWS Security Hub launches 12 new security controls – AWS Security Hub is a cloud security posture management (CSPM) service that performs security best practice checks, aggregates alerts, and enables automated remediation. With the newly released controls, Security Hub now supports three additional AWS services: Amazon Athena, Amazon DocumentDB (with MongoDB compatibility), and Amazon Neptune. Security Hub has also added an additional control against Amazon Relational Database Service (Amazon RDS). AWS Security Hub now offers 276 controls. You can find more information in the AWS Security Hub documentation.

Additional AWS services available in the AWS Israel (Tel Aviv) Region – The AWS Israel (Tel Aviv) Region opened on August 1, 2023. This past week, AWS Service Catalog, Amazon SageMaker, Amazon EFS, and Amazon Kinesis Data Analytics were added to the list of available services in the Israel (Tel Aviv) Region. Check the AWS Regional Services List for the most up-to-date availability information.

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

Other AWS News
Here are some additional blog posts and news items that you might find interesting:

AWS recognized as a Leader in 2023 Gartner Magic Quadrant for Contact Center as a Service with Amazon Connect – AWS was named a Leader for the first time since Amazon Connect, our flexible, AI-powered cloud contact center, was launched in 2017. Read the full story here. 

Generate creative advertising using generative AI –  This AWS Machine Learning Blog post shows how to generate captivating and innovative advertisements at scale using generative AI. It discusses the technique of inpainting and how to seamlessly create image backgrounds, visually stunning and engaging content, and reducing unwanted image artifacts.

AWS open-source news and updates – My colleague Ricardo writes this weekly open-source newsletter in which he highlights new open-source projects, tools, and demos from the AWS Community.

Upcoming AWS Events
Check your calendars and sign up for these AWS events:

Build On AWS - Generative AIBuild On Generative AI – Your favorite weekly Twitch show about all things generative AI is back for season 2 today! Every Monday, 9:00 US PT, my colleagues Emily and Darko look at new technical and scientific patterns on AWS, inviting guest speakers to demo their work and show us how they built something new to improve the state of generative AI.

In today’s episode, Emily and Darko discussed the latest models LlaMa-2 and Falcon, and explored them in retrieval-augmented generation design patterns. You can watch the video here. Check out show notes and the full list of episodes on community.aws.

AWS NLP Conference 2023 – Join this in-person event on September 13–14 in London to hear about the latest trends, ground-breaking research, and innovative applications that leverage natural language processing (NLP) capabilities on AWS. This year, the conference will primarily focus on large language models (LLMs), as they form the backbone of many generative AI applications and use cases. Register here.

AWS Global Summits – The 2023 AWS Summits season is almost coming to an end with the last two in-person events in Mexico City (August 30) and Johannesburg (September 26).

AWS Community Days – Join a community-led conference run by AWS user group leaders in your region: West Africa (August 19), Taiwan (August 26), Aotearoa (September 6), Lebanon (September 9), and Munich (September 14).

AWS re:Invent 2023AWS re:Invent (November 27 – December 1) – Join us to hear the latest from AWS, learn from experts, and connect with the global cloud community. Registration is now open.

You can browse all upcoming in-person and virtual events.

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

— Antje

P.S. We’re focused on improving our content to provide a better customer experience, and we need your feedback to do so. Take this quick survey to share insights on your experience with the AWS Blog. Note that this survey is hosted by an external company, so the link doesn’t lead to our website. AWS handles your information as described in the AWS Privacy Notice.

AWS Weekly Roundup – AWS Storage Day, AWS Israel (Tel Aviv) Region, and More – Aug 8, 2023

Post Syndicated from Veliswa Boya original https://aws.amazon.com/blogs/aws/aws-weekly-roundup-aws-storage-day-aws-israel-tel-aviv-region-and-more-aug-8-2023/

(Editor’s note: Today, we are changing the title of this regular weekly post from AWS Week in Review to AWS Weekly Roundup to better reflect the mix of recent top news and announcements as well as upcoming events you won’t want to miss.)


It’s taken me some time to finally be comfortable with being in front of a camera, a strange thing for a Developer Advocate to say I know! Last week I joined a couple of my team-mates at the AWS London Studios to record a series of videos that will be published in our Build On AWS YouTube Channel. Build On AWS is for the hands-on, technical AWS cloud builder who wants to become more agile and innovate faster. In the channel, you’ll find dynamic, high-quality content that’s designed for developers, by developers!

This video tells you more about what you’ll find in the channel. Check it out and consider subscribing to not miss out when we publish new content.

Now on to the AWS updates. There was a lot of news related to AWS last week, and I’ve compiled a few announcements and upcoming events you need to know about. Let’s get started!

Last Week’s Launches
Here are a few launches from last week that you might have missed:

Microsoft 365 Apps for enterprise now available on Amazon WorkSpaces services – Amazon WorkSpaces is a fully managed, secure, and reliable virtual desktop in the AWS Cloud. With Amazon WorkSpaces, you improve IT agility and maximize user experience, while only paying for the infrastructure that you use. We announced the availability of Microsoft 365 Apps for enterprise on Amazon WorkSpaces. You can bring your own Microsoft 365 licenses (if they meet Microsoft’s licensing requirements) and activate the applications at no additional cost to run Microsoft 365 Apps for enterprise on Amazon WorkSpaces services.

AWS Israel (Tel Aviv) Region is Now Open – You can now securely store data in Israel while serving users in the vicinity with even lower latency. This is because last week we launched the Tel Aviv Region to give customers an additional option for running applications and serving users from data centers located in Israel.

Amazon Connect Launches – This is one of my favorite AWS services to write about because of how Amazon Connect is changing our customers’ engagement with their own customers. Last week, Amazon Connect announced automatic activity scheduling based on shift duration, custom flow block titles, and archiving and deleting flows from the UI, to name a few.

Other AWS News
A few more news items and blog posts you might have missed:

Customizable thresholds for health events supported on Amazon CloudWatch Internet Monitor – Until this announcement, the default threshold for overall availability and performance scores to invoke a health event was 95 percent. Now, you can customize the thresholds for when to invoke a health event for internet-facing traffic between your end users and your applications hosted on AWS.

Improved AWS Backup performance for Amazon S3 buckets – Now you can speed up your initial Amazon S3 backup workflow and back up buckets with more than 3 billion objects due to improvements to the speed of backups by up to 10x for buckets with more than 300 million objects. This performance improvement is automatically enabled at no additional cost in all Regions where AWS Backup support for Amazon S3 is available.

For AWS open-source news and updates, check out the latest newsletter curated by my colleague Ricardo Sueiras to bring you the most recent updates on open-source projects, posts, events, and more.

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

Upcoming AWS Events
We have the following upcoming events:

AWS Storage Day (August 9) – A one-day virtual event where you’ll learn how to prepare for AI/ML with the storage decisions you make now, how to do more with your budget by optimizing storage costs for on-premises and cloud data, and how to deliver holistic data protection for your organization, including recovery planning to help protect against ransomware. Learn more and register here.

AWS Summit Mexico City (August 30) – Sign up for the Summit to connect and collaborate with other like-minded folks while learning about AWS.

AWS Community Days (August 12, 19) – Join these community-led conferences where event logistics and content are planned, sourced, and delivered by community leaders: Colombia (August 12), and West Africa (August 19).

 

P.S. We’re focused on improving our content to provide a better customer experience, and we need your feedback to do so. Take this quick survey to share insights on your experience with the AWS Blog. Note that this survey is hosted by an external company, so the link doesn’t lead to our website. AWS handles your information as described in the AWS Privacy Notice.

– Veliswa

How to Manage Global Sending of SMS with Amazon Pinpoint

Post Syndicated from Tyler Holmes original https://aws.amazon.com/blogs/messaging-and-targeting/how-to-manage-global-sending-of-sms-with-amazon-pinpoint/

Amazon Pinpoint has a global SMS reach, of 240 countries and regions around the world, enabling companies of all sizes to send SMS globally. Unlike the process of sending a personal message from your phone to someone in another country, sending Application to Person (A2P) messages, also known as bulk SMS, involves many more regulations and requirements that vary from country to country. In this post we will review best practices for sending Global SMS and share a selection of AWS resources to help you send SMS globally.

The first thing to understand about delivering SMS around the world is that it takes a vast network of components working seamlessly together around the globe to deliver an SMS globally. The image below gives a simple example of delivering an SMS in the United States. Mobile devices are at the center of this, connecting to mobile carriers or operators, who operate the infrastructure necessary for SMS transmission. Once you hit that send button from AWS, your message travels to an Aggregator, who has connections to Operators, Partners, and/or other Aggregators. The reason for this is that there is no one vendor who delivers globally. AWS uses many Aggregators that both enable us to send globally as well as improve resiliency and deliverability of your messages. The last stop on the journey is the Short Message Service Center (SMSC), a central hub that receives, stores, and forwards text messages. The SMSC acts as a gateway, routing your message to the recipient’s carrier or operator through a series of interconnected networks, thanks to agreements between different carriers known as interconnection agreements. The entire process is facilitated by the Signaling System 7 (SS7), a set of protocols that enables the exchange of information between telecommunication networks, ensuring messages reach their intended recipients.
Diagram showing how SMS is delivered using aggregators
Every country has its own regulations and processes that you need to comply with in order to successfully deliver SMS to handsets that are registered to a particular country. There are some countries with little regulation and others that will block all SMS traffic unless it has been registered with the proper authorities.

Each country’s requirements include the origination identities (OIDs) that their networks support, some of these include long codes (standard phone numbers that typically have 10 or more digits), short codes (phone numbers that contain between four and seven digits), and Sender IDs (names that contain 6–11 alphanumeric characters). Each of these types of origination identities has unique benefits and drawbacks and you will need one for each use case and country you plan on supporting. Here is a list of the countries that AWS currently sends to and the OIDs that are supported.

Pre-Planning and Country Selection
The first step to planning a global roll out of SMS is to know what countries you want to send to and what each of your use cases are. Put together a spreadsheet (Download Here Global SMS Planning Sheet) for each unique use case you have and the countries you plan on sending to with the below key details:

  • The volumes you expect to send to each country
  • The throughput (Also referred to as Messages per Second, MPS, Transactions per Second, or TPS) at which you expect to deliver these messages
  • Whether your use case is one-way or two-way
    • Not all countries support 2-way communications, which is the ability to have the recipient send a message back to the OID. Sender ID also does not support 2-way communication so if you are planning on using Sender ID you will need to account for how to opt recipients out of future communications.
  • Leave a column for the Origination Identity you will use for each country
  • Leave a column for whether this country requires advanced registration
  • Leave a column for any country specific limitations or requirements such as language limitations
  • Leave a column for the estimated time it takes to register
    • This chart has estimates for common countries but there are others that also have lead time in procuring an OID so please open a support case for review

Selecting an Origination Identity

Now that you have these details all in one place consult this table to determine what OIDs each country supports, and, if your use case requires it, which countries support two-way.

In countries where there are multiple options for OIDs there are several guidelines to consider when you’re deciding what type of origination identity to use:

  • Sender IDs are a great option for one-way use cases. However, they’re not available in all countries and if you are needing to opt-out your customers you will need to provide a way for them to do so since they are only one-way.
    • In some countries (such as India and Saudi Arabia), long codes can be used to receive incoming messages, but can’t be used to send outgoing messages. You can use these inbound-only long codes to provide your recipients with a way to opt out of messages that you send using a Sender ID.
  • Short codes are a great option for two-way use cases and have the highest throughput of all OIDs.
    • While short codes have a higher throughput they also come at a much higher cost than other OIDs so weigh your cost against your use case requirements.
  • In some countries, we maintain a pool of shared origination identities. If you send messages to recipients in a particular country, but you don’t have a dedicated origination identity in that country, we make an effort to deliver your message using one of these shared identities.
    • Shared identities are unavailable in some countries, including the United States and China.
    • Shared identities cannot be 2-way so make sure you have a way of opting customers out of communication

With these in mind consult this guide to help you decide which OID to use for each country and use case. Update your sheet as you review each country. Many of our customers opt for a phased roll-out, enabling SMS for the countries that do not require registration and can be put into production swiftly while working through the registration process for those countries that require it and bringing those to production as they are approved. A phased approach is also preferred as it allows customers to monitor for any problems with deliverability with a smaller volume than their full production workload.

Procurement and Registration of Origination Identities

In countries where registration is onerous it is important to have a few things about your process all in one place. Some registrations are very similar in the information that they ask for while others have special processes that you need to follow. Examples include:

Once you have decided on your OIDs for each of your countries you can begin the process of procuring them. Depending on where you plan on sending you may need to open a case to procure them. Short codes you also need to open a case but the process is slightly different so review the documentation here. If you are having trouble making a decision on OIDs you may have the option of engaging with AWS support or your Account Manager dependent on the support level you have opted for on your account.

Testing SMS Sending

Once you have procured OIDs and are ready to begin testing, it is essential that you set up a way of monitoring the events that Pinpoint generates. Pay attention to the Delivery Receipts (DLRs) that are returned back into the event stream. These provide you details on the success or failure of your sends. Pinpoint delivers all events via Amazon Kinesis, which needs to be enabled within each Project you are using. This is a common solution among our customers. It enables the stream, sends it to a user-specified S3 Bucket, and sets up Tables and Views within Amazon Athena, our serverless SQL query engine.. Kinesis can stream to many different destinations, including Redshift and HTTP endpoints, among many others. This gives you flexibility in how you deliver the events to their required locations. Monitoring SMS events is an important part of sending globally, these are the SMS Events that are possible to receive in your stream.

TPS limits can vary depending on the countries you’re sending to and the OIDs you’re using. If there’s a risk of exceeding these limits and triggering rate limiting errors, it’s crucial to devise a strategy for queuing your messages. Keep in mind, Amazon Pinpoint doesn’t offer queueing capabilities. Therefore, message queueing must be incorporated at your application level or by leveraging AWS services. For instance, you could deploy this commonly used architecture that’s adjustable according to your specific use case.

Once you have your monitoring solution in place, you are read to begin testing sends to real destination phone numbers. Keep in mind that at this point you are likely still in the Sandbox for SMS. This means you have much lower quotas for sending and can only send to verified phone numbers or the SMS Simulator numbers. Pinpoint includes an SMS simulator, which you can use to send text messages and receive realistic event records to 51 commonly sent to countries. Messages sent to these destination phone numbers are not sent over the carrier network but do incur the standard outbound SMS messaging rate for the country that the simulated phone number is based in.

Best Practices for Sending
Before beginning There are two common ways of sending SMS via Pinpoint. The first option is the Pinpoint API using the SendMessages Action, which you can send a direct message to as many as 100 recipients at a time. The second option is to use the SMS and Voice v2 API and the SendTextMessage Action, which has more options available to configure your sends and can send to a single recipient with each call. The V2 API is the preferred way of sending as it allows for more fine grained control over your messages and is the API upon which new functionality will be built. Keep in mind that sending via the API does not attribute any metrics back to an endpoint unless you are specifying an endpoint ID in your call, so if you are using other features of Pinpoint such as campaigns or journeys or sending via other channels such as email you will need to consider your strategy for measuring success and how you will tie all of your communication efforts together.

When sending SMS Pinpoint includes logic for selecting the best OID to send from based on the country code. If there are multiple OIDs available to send to a particular country Pinpoint will default to the highest throughput OID available in your Account/Region. If there are not OIDs specific to the country being sent to Pinpoint will default to SenderID or to a shared OID owned by Pinpoint in that order, if the country allows these OIDs to be used. Given this functionality the best practice for sending SMS is to not specify the OID needed to send to a specific country and to allow Pinpoint to select. You can restrict Pinpoint to send to only those countries that you have OIDs for by using Pools, and turning off Shared Routes, more on this below.

If you have multiple use cases and need to specify the correct OID for each, this is where the V2 API is useful. OIDs can be attached to Pools, which can be configured to serve a particular use case, and the pool can be specified in your SendTextMessage call. Sending using a PoolID and allowing Pinpoint to select the right OID from that pool for the destination phone number simplifies your sending process. This blogpost details the process for creating Pools and using them to send SMS.

As mentioned above Pools also serve an additional use case, which is to limit message sending to specific countries. Some countries allow messages without an OID. If you don’t modify your settings to disable this feature, Pinpoint will attempt to deliver messages to these countries, even if you don’t have an explicit OID for them. Restricting SMS sends only to countries that you have OIDs for can be accomplished by using Pools and configuring “SharedRoutesEnabled“ to false by using the UpdatePool Action. Once configured you will receive an error back if attempting to send to a destination phone number that you do not have an OID for in the Pool. This configuration gives you the ability to control your costs while simplifying your process.

Managing Opt-Outs

As we have seen, managing SMS in an environment of increasing global regulation is challenging. An area of importance that needs to be configured is how you plan on managing the ability for recipients to opt out of your communications. Pinpoint can automatically opt your customers out of SMS communications using predefined keywords such as, “stop” or “unsubscribe.” However, this would make for an Account wide opt-out, and not ideal for customers that have multiple use cases such as OTP and Marketing communications. This blogpost details the process of managing opt-outs for multiple use cases. The configuration is enabled through the V2 API and is another reason to standardize your process on this API.

Monitoring Sending

The last step in ensuring success for SMS sending is having a solid platform for monitoring your sending. SMS is not a guaranteed delivery channel. You will always receive an event for a successful send in the event stream but there is no guarantee of a return status event, if a DLR from a carrier is not sent. A list of SMS Events and possible statuses can be found here.

The first Event you should see returned when watching the Event Stream for an SMS send activity is the “PENDING” event. This means we’ve sent the message to the carrier, where it’s buffered, and we’re waiting for the carrier to return a status message. There are no status messages between the “PENDING” state and the “whatever happens next” state, so if the carrier is retrying, we simply stay in PENDING and do not create more events. If a message is successfully delivered and a DLR is sent back from the carrier then a new event will be generated with a status of “SUCCESSFUL/DELIVERED.”

Make sure to review all of the possible values for the record_status attribute so that you are aware of varying issues with your sending that can arise. For example, statuses such as “Blocked,” “Spam,” and “Carrier_Blocked“ can indicate systemic issues that should be investigated.

Updates sent from a carrier via a DLR can be delayed for up to 72 hours or never sent at all. This varies based on the carrier and the country being sent to. Should you require a higher level of reliability, you need to establish business logic around monitoring SMS messages. If messages remain in a PENDING status longer than your business requirements permit, you must make a decision on how to handle them. You need to consider whether missed or duplicated messages are acceptable, or if it’s preferable to retry messages that are stuck in pending. The following is an example architecture for failed SMS retries that you can adjust to your needs.

Conclusion

This post covers the general process for getting started with Global SMS but as you have learned each country presents a different challenge and the regulatory environment is constantly evolving. It’s important to make sure that you are receiving messages from AWS that detail new regulations, new feature launches, and other major announcements to continually improve your process and make sure your SMS are delivering at the highest rate possible.

Take the time to plan out your approach, follow the steps outlined in this blog, and take advantage of any resources available to you within your support tier.

Decide what origination IDs you will need here
Review the documentation for the V2 SMS and Voice API here
Review the Pinpoint API and SendMessage here
Check out the support tiers comparison here

Resources:
https://docs.aws.amazon.com/pinpoint/latest/userguide/channels-sms-countries.html
https://aws.amazon.com/blogs/messaging-and-targeting/how-to-utilise-amazon-pinpoint-to-retry-unsuccessful-sms-delivery/
https://datatracker.ietf.org/doc/html/draft-wilde-sms-uri-20#section-4
https://docs.aws.amazon.com/pinpoint/latest/developerguide/event-streams-data-sms.html
https://docs.aws.amazon.com/pinpoint/latest/userguide/channels-sms-limitations-opt-out.html
https://docs.aws.amazon.com/pinpoint/latest/userguide/channels-sms-simulator.html

Announcing General Availability of Step-by-Step Guides for Amazon Connect Agent Workspace

Post Syndicated from Veliswa Boya original https://aws.amazon.com/blogs/aws/announcing-general-availability-of-step-by-step-guides-for-amazon-connect-agent-workspace/

At AWS re:Invent 2022 we announced the availability of step-by-step guides for Amazon Connect agent workspace in preview. My colleagues who collaborated to write the announcement post wrote about some of the challenges that contact centers face with training new agents to get up to speed with their agent desktop. They also mentioned that until agents become proficient, it takes them longer to address customer needs effectively, resulting in customer dissatisfaction.

Amazon Connect agent workspace was announced in 2021 and is a single, intuitive application that provides contact center agents with the tools that are required to onboard an agent quickly, resolve issues efficiently, and improve the customer experience. With Amazon Connect agent workspace, the agent is provided with all the tools on one screen. To think of the agent workspace, imagine the agent accepting a call, a chat, or a task and being given the necessary information about the customer and the case, plus real-time recommendations, all in one place without the need to switch between applications.

Step-by-step guides enable organizations to provide customizable experiences for their agents within the workspace, enabling them to deliver exceptional service from their first day on the job by surfacing relevant information and actions that the agent requires in order to resolve customer issues faster. This is because the step-by-step experience guides agents by identifying customer issues and then recommending subsequent actions, ensuring that the agent never has to guess or rely on past experience to know what comes next. This is helpful for both new and experienced agents. New agents can learn the system and get acquainted with their job and experienced agents can keep to the organization’s standard operating procedures instead of diverging in how they handle the same type of customer request.

Because of this intuitive experience, onboarding time for agents can be reduced by up to 50 percent, time to proficiency for the agent can be reduced by up to 40 percent, and contact handle time is reduced by up to 35 percent ultimately resulting in an improved and consistent customer experience.

A High-Level Overview of Step-by-Step Guides
During the announcement of step-by-step guides in preview, I was fascinated to learn that the experience was researched and developed in the context of Amazon Customer Service. However, step-by-step guides can also be generalized to apply to other types of organizations and use cases including the following:

  • Retail – You can customize guides to suit your retail organization, for example, guides for returning a purchase by a customer.
  • Financial Services – An example would be adding an authorized user to a credit card. Using guides, the agent can help the customer capture new user information and handle approvals through a single workflow that is consolidated within the guides.
  • Hospitality – A great example here would be creating a new reservation at a hotel by consolidating all the processes involved into a single workflow.
  • Embed as a Widget – With this, you can embed guides as a widget in your existing CRM or use APIs to bring guides to a custom workspace that you are already using in your organization.

The preview announcement post provides a deep dive into how to get started with step-by-step guides. It also shows how to deploy a sample guided experience and demonstrates how to customize guides to meet business needs. In this post we look at a high-level overview of what the agent, and the manager, can expect from step-by-step guides.

Agent experience
Step-by-step guides help with onboarding and ramping up of new agents and making them proficient faster by surfacing contextually relevant information and actions needed by agents. The intuitive experience of step-by-step guides provides agents with clear instructions of what they should be doing at any point in time when handling a particular customer case and supports agents in managing complex cases more accurately by automatically identifying issues.

As an example, when a customer calls, the agent workspace automatically presents the agent with the likely issue based on the customer’s history or current context (for instance, making a flight reservation). Then, the step-by-step experience guides the agent through the actions needed to resolve the issue quickly (such as booking a hotel after the flight reservation has been completed).

The following screenshot provides a visual image of how this might look.

Step-by-step Guides

In the UI, the agent is provided with a sequence of simple UI pages to let them focus on one thing at a time, whether that’s an input field or a question to ask the customer. They can go step by step, getting the right information that they need to help the customer’s issue. Along the way, the agent receives scripting that they can read to the customer upon successful completion of the process.

The agent can always escape out of this workflow if it turns out that the workspace surfaced the wrong one, and they can find other workflows by searching for the correct one. This allows them to self-serve and find the right solution in case what was predicted by the step-by-step guides based on the context of the contact wasn’t perfectly aligned to what they needed.

Manager experience
Amazon Connect already has a low-code, no-code builder known as Amazon Connect Flows. Flows provide a drag-and-drop experience for building IVRs, chatbots and routing logic for customers. To enable the same low-code, no-code configuration of step-by-step guides, managers are now provided with a new block within Flows known as the Show View block. The drag-and-drop experience of configuring step-by-step guides ensures that the manager no longer needs to have developers write code to build the custom workflows for the agent. Managers also no longer need to rely on static and difficult-to-follow instructions to use later to train agents.

Example of the Show View block within the Contact Flow editor

Example of the Show View block within the Contact Flow editor

Step-by-step guides are quickly created within the show view block with the help of five pre-configured views. Views are UI templates that can be used to customize the agent’s workspace, and each view is configurable. For example, you can use views to display contact attributes to an agent, provide forms for entering disposition codes, provide call notes, and present UI pages for walking agents through step-by-step guides.

The following example shows a view that we can use to create a guide for an agent that needs to book a round-trip flight for a customer. Booking this trip requires scheduling a flight to and from the destination, collecting traveler information, and asking about additional add-ons. With the form view, agents don’t have to recall all these specific steps; they can follow the wizard in their agent workspace. For each step, the agent is given form fields to fill in or options to choose from in order to quickly book the customer’s flight.

Example UI (View)

Example UI (View)

Step-by-step guides also help business operation teams figure out new ways to ensure that their agents are operating well and adjusting to new use cases. Step-by-step guides provide managers with insights into what agents do during a contact. During a workflow, data about what is shown to an agent, the decisions they made, the amount of time they spent on different steps, and what actions they took is captured and stored as a log record. Managers can use this data to improve their workflows and the agent and customer experiences.

Conclusion
In this post we discussed what step-by-step guides offer the agent and the manager of a contact center. Our customers are excited about how the guided experience consolidates actions into workflows and reduces the number of screens for their agents – at times from five screens down to one. In addition to all the benefits we’ve discussed in this post, guides provide you with opportunities to save between 15 – 20 percent on maintenance cost.

Now Available
Step-by-step guides are now generally available in all Regions where Amazon Connect is available, except AWS GovCloud (US-West) and Africa (Cape Town).

To learn more, refer to the Getting started with step-by-step guides for the Amazon Connect agent workspace post, and please send feedback to AWS re:Post for Amazon Connect or through your usual AWS support contacts.

– Veliswa x.

Automating adverse events reporting for pharma with Amazon Connect and Amazon Lex

Post Syndicated from Siva Thangavel original https://aws.amazon.com/blogs/architecture/automating-adverse-events-reporting-for-pharma-with-amazon-connect-and-amazon-lex/

Every pharmaceutical company manufacturing medicine must provide customers nationwide with a method to report adverse events following medicine usage as well as emergency assistance as needed. To comply with regulatory policy and enable an Adverse Events Reporting System (AERS), pharma companies must provide dedicated, toll-free phone numbers and contact center agents to handle inbound calls.

But they must also be prepared for sudden spikes in call volume, which can increase contact center agents’ workloads and lead to long wait times for customers. With these limitations comes the possibility that customers may not be able to report adverse events.

Further still, as medicine status keeps changing, all agents must be retrained to handle calls and extend support. Pharma companies incur significant costs for training and onboarding additional agents, as well as the physical infrastructure to support their work.

To overcome these challenges, we designed a self-service Interactive Voice Response (IVR) solution with Amazon Connect. The IVR solution handles customer calls without agent involvement. It captures customer information and records data into an enterprise AERS. It also provides an option to receive a link to an Adverse Events (AE) portal using Short Message Service (SMS), or to be routed to a live agent queue.

In this blog post, we introduce a reference architecture for this use case. This framework can help other pharma companies solve similar problems.

Solution overview

Let’s explore how the IVR solution architecture routes customer calls step by step, as shown in Figure 1.

Adverse events reporting architecture diagram

Figure 1. Adverse events reporting architecture diagram

  1.  Callers who dial in to report a medicine-related AE are routed to the Amazon Lex chatbot through IVR in Amazon Connect.
  2. Callers can proceed to IVR self-service functions, such as understanding the intent of a customer call and the AE.
  3. AEs are analyzed with Amazon SageMaker for a decision on whether to complete the call on IVR or forward it to an agent.
  4. If the caller remains on the self-service option, the bot captures information from 15 to 20 essential questions.
  5. The bot follows a hybrid workflow that allows for guided responses where appropriate and free-text conversations using AWS Lambda. It confirms captured AE information with the caller before closing the call and submitting information to the AERS system.
  6. The bot provides the option to route the call to a human agent contextually.
  7. The bot provides the option to share an AE reporting link over SMS using Amazon Simple Notification System (SNS), so the caller can access it through a mobile device to continue AE reporting outside of the call.
  8. The bot records customer interactions in AERS using Amazon DynamoDB, leveraging the current validated process used by the AE portal team
  9. The bot makes call recordings available for auditing, monitoring, and training purposes. These recordings are not be provided to live agents.
  10. Standard analytics are available to help the business continuously train the bot and measure its performance.

Leveraging IVR as an extended solution

Recorded customer calls can be used for further analytics with Amazon Transcribe. Actionable insights can be derived from the text using a machine learning (ML) model such as AE detection at scale. A (Named Entity Recognition model (NER) model can also identify medicines and caller types.

Further, all recorded calls may be stored in a secure AWS ecosystem and archived for longer durations for compliance purposes. Storage costs can be optimized by setting up a policy to move old calls to Amazon Simple Storage Service Glacier (Amazon S3 Glacier) storage classes and calls over two years old to the Amazon S3 Deep Glacier storage class. This results in significant cost saving and helps companies archive at scale.

Finally, the Amazon Lex bot can be enhanced and continuously trained with additional intents and utterances to handle complex AE reporting for various drugs. This provides significant cost saving and operational efficiencies as bots can be trained faster than human agents, as well as at scale.

Conclusion: Using IVR to better manage AE reporting

This IVR solution was deployed for a pharma company and helped handle unusually high call volumes for AE reporting with its current agent population. It resulted in cost savings in contact center operations and significantly improved the customer experience by reducing wait times.

The IVR solution can also be used with any existing contact center platform to first forward the calls to Amazon Connect for initial triage, and then handover to existing platforms for agent involvement. This adds intelligence to existing contact centers.

This blog post demonstrates how pharma companies can leverage the self-service option for AERS to handle any AE reporting call. With solution enhancements using Amazon SageMaker models, it can quickly be transformed to handle calls for any medicine. They can also:

  • Incorporate related information into the model, such as the age, gender, or existing AEs to further improve the ML prediction performance
  • Leverage audio data augmentation plus handcrafted features to help yield better predictions
  • Use the audio-based diagnostic prediction in an Amazon Connect contact flow to triage the targeted group of incoming calls and escalate to a doctor for follow up if necessary
  • Allow call center agents to use the intelligence provided by the acoustic classification in conjunction with Contact Lens for Amazon Connect, which provides a turn-by-turn transcript; real-time alerts; automated call categorization based on keywords and phrases; sentiment analysis, and sensitive data redaction—truly making it a real-time intelligent solution.

The IVR solution can also be used for other industry use cases where a series of data is collected from customers. This solution improves the customer experience and can be implemented without increasing call center agent counts.

How to encrypt sensitive caller voice input in Amazon Lex

Post Syndicated from Herbert Guerrero original https://aws.amazon.com/blogs/security/how-to-encrypt-sensitive-caller-authentication-voice-input-in-amazon-lex/

In the telecommunications industry, sensitive authentication and user data are typically received through mobile voice and keypads, and companies are responsible for protecting the data obtained through these channels. The increasing use of voice-driven interactive voice response (IVR) has resulted in a need to provide solutions that can protect user data that is gathered from mobile voice inputs. In this blog post, you’ll see how to protect a caller’s sensitive voice data that was captured through Amazon Lex by using data encryption implemented through AWS Lambda functions. The solution described in this post helps you to protect customer data received through voice channels from inadvertent or unknown access. The solution also includes decryption capabilities, which give an authorized administrator or operator the ability to decrypt user data from a Lambda console.

Solution overview

To demonstrate the IVR solution described in this post, a caller speaks two sensitive pieces of data—credit card number and zip code—from an Amazon Connect contact flow. The spoken values are encrypted and returned to the contact flow to be stored in contact attributes. The encrypted ciphertext is retained as a contact attribute for decryption purposes. Amazon CloudWatch Logs is enabled in the contact flow, but only the encrypted values are logged in log streams.

For this solution, conversation logs for this Amazon Lex bot are not enabled. An operator with assigned AWS Identity and Access Management (IAM) permissions can monitor the logged encrypted entries from CloudWatch Logs. For more information, see Working with log groups and log streams in the Amazon CloudWatch Logs User Guide.

Solution architecture

Figure 1 shows the overview of the solution described in this blog post.

Figure 1: Example of solution architecture

Figure 1: Example of solution architecture

Figure 1 shows the following high-level steps of the solution, and the number labels correspond to the following steps.

  1. A caller places an inbound call.
  2. An Amazon Connect contact flow leverages a Get customer input block, backed by an Amazon Lex bot, to prompt the caller for numerical data.
  3. The Amazon Lex bot invokes the Lambda function dev-encryption-core-EncryptFn.
  4. The Lambda function uses the AWS Encryption SDK to encrypt the caller’s plain text data.
  5. The AWS Encryption SDK obtains encryption keys from AWS Key Management Service (AWS KMS).
  6. The caller’s data is encrypted by using the AWS KMS keys obtained from AWS KMS.
  7. The Lambda function appends the encrypted data to the Amazon Lex bot session attributes.
  8. Amazon Lex returns the fully encrypted data back to Amazon Connect.

Overview of a contact flow

Figure 2: Contact flow captures input values using Amazon Lex and returns their encrypted values

Figure 2: Contact flow captures input values using Amazon Lex and returns their encrypted values

Figure 2 shows an overview of the contact flow, which has two main steps:

  1. The first numerical data (in this example, an encrypted credit card number value) is stored in contact attributes.
  2. The second numerical data (in this example, an encrypted zip code value) is stored in contact attributes.

Prerequisites

This solution uses the following AWS services:

The following need to be installed in your local machine:

To implement the solution in this post, you first need the Amazon Connect instance prerequisite in place.

To set up the Amazon Connect instance (if none exists)

  1. Create an Amazon Connect instance with a claimed phone number and a configured Amazon Connect user linked to a basic routing profile. For more information about setting up a contact center, see Set up your contact center in the Amazon Connect Administrator Guide.
  2. Assign the CallCenterManager or Admin security profile to an Amazon Connect user.
  3. In the newly created Amazon Connect instance, under the Overview section, find the access URL with the format
    https://<aliasname>.awsapps.com/connect/login

    • Make note of the access URL, which you will use later to log in to the Amazon Connect Dashboard.
  4. Log in to your Amazon Connect instance with a Connect user that has Admin or CallCenterManager permissions.

Solution procedures

This solution includes the following procedures:

  1. Clone the project or download the solution zip file.
  2. Create AWS resources needed for encryption and decryption.
  3. Configure the Amazon Lex bot in Amazon Connect.
  4. Create the contact flow in Amazon Connect.
  5. Validate the solution.
  6. Decrypt the collected data.

To clone or download the solution

  • Log in to the GitHub repo.
  • Clone or download the solution files to your local machine.

The downloaded file contains the artifacts needed for the deployment.

To create AWS resources needed for encryption and decryption

  1. From the command line, change directory to the project’s root directory.
  2. Run npm install.
  3. Run npm run build to transpile TypeScript to JavaScript and package code and its dependencies before deploying to AWS.
  4. Run cdk deploy CoreStack.

To configure the Amazon Lex bot in your Amazon Connect instance

  1. In the Amazon Connect console, choose Contact flows and scroll to the Amazon Lex section.
    Figure 3: Select Contact flows

    Figure 3: Select Contact flows

  2. From the Bot menu, select secure_LexInput(Classic). Then select +Add Amazon Lex Bot.
    Figure 4: Configure the Amazon Lex bot to Amazon Connect

    Figure 4: Configure the Amazon Lex bot to Amazon Connect

To import contact flow into Amazon Connect

  1. In the Amazon Connect console, choose Overview, and then choose Login as administrator.
  2. From the Routing menu on the left side, choose Contact flows to show the list of contact flows.
  3. Choose Create Contact flow.
  4. Choose the arrow to the right of the Save button and choose Import flow (beta). This imports the contact flow that you previously downloaded in the procedure To clone or download the solution.

    The contact flow already has the Amazon Lex bot configured.

    Figure 5: Select Import flow (beta)

    Figure 5: Select Import flow (beta)

  5. In the upper right corner of the contact flow, choose Save, and then choose OK to save the changes.
  6. Choose Publish to make the contact flow ready for use during the validation steps.
  7. (Optional) Claim a phone number (if none is available), using the following steps:
    1. In the Connect Dashboard, on the navigation menu, choose Channels, and then choose Phone numbers.
    2. On the right side of the page, choose Claim a number.
    3. Select the DID (Direct Inward Dialing) tab. Use the drop-down arrow to choose your country/region. When numbers are returned, choose one.
    4. Write down the phone number. You call it later in this post.
  8. (Optional) On the Edit Phone number page, in the Description box, you can type a note if desired.
  9. To assign the contact flow to your claimed phone number, for Contact flow / IVR, choose the drop-down arrow, and then choose Secure_Lex_Input.
  10. Choose Save.
    Figure 6: Under Contact flow / IVR, select the imported contact flow

    Figure 6: Under Contact flow / IVR, select the imported contact flow

For more information, see Set up phone numbers for your contact center in the Amazon Connect Administrator Guide.

To validate the solution

  1. Dial the test phone number to go through the voice prompt flow.
  2. When prompted, speak a 16-digit credit card number (you have a maximum of two retries), then speak a 5-digit zip code (also a maximum of two retries).
  3. After you complete your test call, review the log streams in Amazon CloudWatch Logs to confirm that the digits that you entered are now encrypted and stored as a contact attribute. The two entered values zipcode and creditcard are stored in contact attributes. Both are encrypted.
    Figure 7: Sample log showing encrypted values for zipcode and creditcard

    Figure 7: Sample log showing encrypted values for zipcode and creditcard

  4. Log in to your Amazon Connect Dashboard as a Supervisor. The URL is provided after the connect instance has been created. In the navigation menu, choose Contact search.
    Figure 8: Choose Contact search to look for the call information

    Figure 8: Choose Contact search to look for the call information

  5. Locate your inbound call on the Contact search list. Note that it can take up to 60 seconds for data to appear in the Contact search list.
  6. Select the Contact ID for your call.
    Figure 9: The Contact search showing the contact details for your test call

    Figure 9: The Contact search showing the contact details for your test call

  7. Copy the encrypted values for creditcard and zipcode and make note of them; you will use these values in the next procedure.
    Figure 10: Contact attributes stored in a contact flow are registered as part of the contact details

    Figure 10: Contact attributes stored in a contact flow are registered as part of the contact details

To decrypt the collected data

  1. In the AWS Lambda console, choose Functions.
  2. Use the Search bar to look for the dev-encryption-core-DecryptFn Lambda function, and then select the name link to open it.
  3. Under folder encryption-master, open the test folder. Under the tab \events, locate the file decrypt.json.
  4. Use the following steps to create a sample test event in the console by using the contents from decrypt.json. For more details, see Testing Lambda functions in the console.
    1. Choose the down arrow on the right side of Test.
    2. Choose Configure test event.
    3. Choose Create new test event.
    4. For Event name, enter decryptTest.
    5. Paste the contents from decrypt.json. 
      {
    "Details": {
        "Parameters": {
            "encrypted": "<encrypted-value-here>"
        }
    }
}

    6. Choose Save.
  5. Use the encrypted values saved in the Validate a solution procedure and replace the ones in the recently created test event.
    Figure 11: Replace the creditcard or zipCode values with the ones from the Contact Search page

    Figure 11: Replace the creditcard or zipCode values with the ones from the Contact Search page

  6. Choose Test. The output from the test shows the values decrypted by the Lambda function. This is shown in Figure 12 under the Execution result tab.
    Figure 12: Result from the decryption operation

    Figure 12: Result from the decryption operation

Note: Make sure that only the appropriate authorized administrator or operator, application, or AWS service is able to invoke the decryption Lambda function.

You have now successfully implemented the solution by encrypting and decrypting the voice input of your test call, which you collected through Amazon Lex.

Cleanup

To avoid incurring future charges, follow these steps to clean up the deployed resources that you created when implementing this solution.

To delete the Amazon Connect instance

  1. In the Amazon Connect console, under Instance alias, select the name of the Amazon Connect instance, and choose Delete.
  2. When prompted, type the name of the instance, and then choose Delete.

To delete the Amazon Lex bot

  1. In the Amazon Lex console, choose the bot that you created in the To configure the Amazon Lex bot procedure.
  2. Choose Delete, and then choose Continue.

To delete the AWS CloudFormation stack

  1. In the AWS CloudFormation console, on the Stacks page, select the stack you created in the procedure To create AWS resources needed for encryption and decryption.
  2. In the stack details pane, choose Delete.
  3. Choose Delete stack when prompted. This deletes the Amazon S3 bucket, IAM roles and AWS Lambda functions you created for testing. This will also schedule a deletion date on the AWS KMS key.

Conclusion

In this post, you learned how an Amazon Connect contact flow can collect voice inputs from a caller by using Amazon Lex, and how you can encrypt these inputs by using your own AWS KMS key. This solution can help improve the security of voice input that is collected through Amazon Connect. For cost information, see the Amazon Connect pricing page.

For more information, see the blog post Creating a secure IVR solution with Amazon Connect and the topic Encrypt customer input (using OpenSSL) in the Amazon Connect Administrator Guide. As previously mentioned, the increasing use of voice-driven IVR has resulted in a need to provide solutions that can protect user data gathered from mobile voice inputs.

Additional resources include the AWS Lambda Developer Guide, the Amazon Lex Developer Guide, the Amazon Connect Administrator Guide, the AWS Nodejs SDK, and the AWS SDK for Python (Boto3).

If you need help with setting up this solution, you can get assistance from AWS Professional Services. You can also seek assistance from Amazon Connect partners available worldwide.

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

Want more AWS Security news? Follow us on Twitter.

Herbert Guerrero

Herbert Guerrero

Herbert is a Senior Proserve Consultant for Connect. He enjoys designing and developing high-usability and scalable solutions. Understanding success criteria helps Herbert work backwards and deliver well-architected solutions. His engineering background informs the way he engages with customers’ mental models of what their solutions should look like.

Ed Valdez

Ed Valdez

Ed is a Specialty Consultant with Amazon Web Services. As a software development professional with over 23 years of experience, he specializes on designing and delivering customer-centric solutions within the contact center domain.

Happy New Year! AWS Week in Review – January 9, 2023

Post Syndicated from Channy Yun original https://aws.amazon.com/blogs/aws/happy-new-year-aws-week-in-review-january-9-2023/

Happy New Year! As we kick off 2023, I wanted to take a moment to remind you of some 2023 predictions by AWS leaders for you to help prepare for the new year.

You can also read the nine best things Amazon announced and AWS for Automotive at the Consumer Electronics Show (CES) 2023 in the last week to see the latest offerings from Amazon and AWS that are helping innovate at speed and create new customer experiences at the forefront of technology.

Last Year-End Launches
We skipped two weeks since the last week in review on December 19, 2022. I want to pick some important launches from them.

Last Week’s Launches
As usual, let’s take a look at some launches from the last week that I want to remind you of:

  • Amazon S3 Encrypts New Objects by Default – Amazon S3 encrypts all new objects by default. Now, S3 automatically applies server-side encryption (SSE-S3) for each new object, unless you specify a different encryption option. There is no additional cost for default object-level encryption.
  • Amazon Aurora MySQL Version 3 Backtrack Support – Backtrack allows you to move your MySQL 8.0 compatible Aurora database to a prior point in time without needing to restore from a backup, and it completes within seconds, even for large databases.
  • Amazon EMR Serverless Custom Images – Amazon EMR Serverless now allows you to customize images for Apache Spark and Hive. This means that you can package application dependencies or custom code in the image, simplifying running Spark and Hive workloads.
  • The Graph Explorer, Open-Source Low-Code Visual Exploration Tool – Amazon Neptune announced the graph-explorer, a React-based web application that enables users to visualize both property graph and Resource Description Framework (RDF) data and explore connections between data without having to write graph queries. To learn more about open source updates at AWS, see Ricardo’s OSS newsletter.

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

Other AWS News
Here are some other news items that you may find interesting in the new year:

  • AWS Collective on Stack Overflow – Please join the AWS Collective on Stack Overflow, which provides builders a curated space to engage and learn from this large developer’s community.
  • AWS Fundamentals Book – This upcoming AWS online book is intended to focus on AWS usage in the real world, and goes deeper with amazing per-service infographics.
  • AWS Security Events Workshops – AWS Customer Incident Response Team (CIRT) release five real-world workshops that simulate security events, such as server-side request forgery, ransomware, and cryptominer-based security events, to help you learn the tools and procedures that AWS CIRT uses.

Upcoming AWS Events
Check your calendars and sign up for these AWS events in the new year:

  • AWS Builders Online Series on January 18 – This online conference is designed for you to learn core AWS concepts, and step-by-step architectural best practices, including demonstrations to help you get started and accelerate your success on AWS.
  • AWS Community Day Singapore on January 28 – Come and join AWS User Group Singapore’s first AWS Community Day, a community-led conference for AWS users. See Events for Developers to learn about developer events hosted by AWS and the AWS Community.
  • AWS Cloud Practitioner Essentials Day in January and February – This online workshop provides a detailed overview of cloud concepts, AWS services, security, architecture, pricing, and support. This course also helps you prepare for the AWS Certified Cloud Practitioner examination.

You can browse all upcoming in-person, and virtual events.

That’s all for this week. Check back next Monday for another Week in Review!

— Channy

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