8/23/2024, 12:00:00 AM ~ 8/26/2024, 12:00:00 AM (UTC)
Recent Announcements
Knowledge Bases for Amazon Bedrock supports Anthropic’s Claude 3.5 Sonnet
Knowledge Bases for Amazon Bedrock securely connects foundation models (FMs) to internal company data sources for Retrieval Augmented Generation (RAG) to deliver relevant, context-specific, and accurate responses. Anthropic’s Claude 3.5 Sonnet foundation model is now generally available on Knowledge Bases.\n Anthropic’s Claude 3.5 Sonnet—the first model in the forthcoming Claude 3.5 model family—has a 200,000 context window (roughly 150,000 words, or around 300 pages of material) and raises the industry bar for intelligence, outperforming other generative AI models on a wide range of evaluations. Claude 3.5 Sonnet is well-suited for tasks that require complex reasoning, quick outputs, and RAG. Additionally, Claude 3.5 Sonnet is supported through the fully managed RetrieveAndGenerate API.
Anthropic’s Claude 3.5 Sonnet model support for Amazon Bedrock Knowledge Bases is now generally available in the US East (N. Virginia), US West (Oregon), Europe (Frankfurt) and Asia Pacific (Tokyo) AWS Regions. To learn more, read the AWS News launch blog and Claude in Amazon Bedrock product page. To get started, refer to the Knowledge Bases for Amazon Bedrock documentation and visit the Amazon Bedrock console.
Amazon Connect provides new ways to configure callbacks
Amazon Connect now allows you to configure flows to take actions on callbacks prior their creation and while they are in queue. For example, you can now automate sending a notification to a customer via SMS before calling them back, update callback attributes based on latest customer data for agents to reference, or even terminate the callback if the issue has already been resolved. You can also now run flows to dynamically re-prioritize and transfer callbacks to another queue based on customer information from Customer profiles or third-party applications, or if it’s just taking too long for the callback queue to drain.\n This feature is available in all AWS regions where Amazon Connect is offered. To learn more about this feature, see the Amazon Connect administrator guide. To learn more about Amazon Connect, the AWS cloud-based contact center, please visit the Amazon Connect website.
AWS Blogs
AWS Japan Blog (Japanese)
- Responding to CloudWatch alarms with Amazon Bedrock Insights
- AWS Observability Improvements — Unlock the Power of Amazon CloudWatch Alarms
- Use Amazon Bedrock’s Generative AI to Build Personalized Student Companions
- Use AWS CodeBuild to add macOS to your continuous integration pipeline
- Finally Open — AWS Asia Pacific (Malaysia) Region
- The “Government Cloud Usage Task List” for local government customers has been updated
- The Possibilities of Generative AI Seen at the PartyRock Exhibit — Paths to Business Utilization (AWS Summit Japan 2024)
- Hints for using government clouds “Points to be aware of when estimating”
AWS Contact Center
AWS Database Blog
AWS DevOps & Developer Productivity Blog
- Publish packages to AWS CodeArtifact using Amazon CodeCatalyst Actions
- Best Practices for working with Pull Requests in Amazon CodeCatalyst
- Accessing Amazon Q Developer using Microsoft Entra ID and VS Code to accelerate development
- How A/B Testing and Multi-Model Hosting Accelerate Generative AI Feature Development in Amazon Q