|
|
Last week, Anthropic’s Claude Sonnet 4.5 – the world’s best coding model according to SWE-Bench – was made available in the Amazon Q Command Line Interface (CLI) and Kiro. I’m excited about this for two reasons:
First, a few weeks ago I spent 4 intensive days with a global customer delivering an AI-enabled developer workshop where I experienced first-hand how Amazon Q CLI increases developer productivity. During the workshop, the customer was able to add a new feature to their application in one day using the Amazon Q CLI, which would traditionally have taken them at least a couple of weeks. I know that with Anthropic’s Claude Sonnet 4.5 in the Amazon Q CLI, developer productivity will be further enhanced.
Second, I started preparing for my code talk at AWS re:Invent 2025, where my co-presenter and I will show live coding to modernize a legacy codebase using Kiro. I can’t wait to use Anthropic’s Claude Sonnet 4.5 in Kiro to create a live demo. To see this demo and over a thousand other sessions on cloud and AI, join us at AWS re:Invent 2025 in Las Vegas from December 1-5.
Last week’s launch
Here are some launches that caught my eye:
- Claude Sonnet 4.5 Availability on Amazon Bedrock – Anthropic’s most intelligent model, best for coding and complex agents, is now available on Amazon Bedrock. By using Claude Sonnet 4.5 in Amazon Bedrock, developers gain access to a fully managed service that not only provides a unified API for base models (FM), but keeps their data under complete control with enterprise security and optimization tools.
- AWS Outposts supports third-party storage integration with Dell and HPE – AWS Outposts third-party storage integration now includes Dell PowerStore and HPE Alletra Storage MP B10000 systems, joining the list of existing integrations with on-premises NetApp and Pure Storage FlashArray enterprise storage arrays. This integration serves three main purposes. First, it helps you maintain your existing storage infrastructure while migrating VMware workloads to AWS. Second, it helps you meet strict data residency requirements by keeping your data on-premises while using AWS services. Third, it means you can use AWS Outposts with third-party storage arrays through AWS tools.
- Amazon ECS Managed Instances Now Available – Amazon ECS Managed Instances for Containerized Applications is a new fully managed compute option for Amazon ECS designed to eliminate infrastructure management overhead while giving you access to all of Amazon EC2’s capabilities. ECS Managed Instances help you quickly launch and scale your workloads while increasing performance and reducing total cost of ownership.
- Application Map Now Generally Available for Amazon CloudWatch – Amazon CloudWatch now helps you monitor large-scale distributed applications by automatically discovering and organizing services into groups based on configurations and their relationships. With this new application performance monitoring (APM) capability, you can quickly visualize which applications and dependencies to focus on when troubleshooting distributed applications.
- Amazon Bedrock AgentCore Model Context Protocol (MCP) Server Now Available – With built-in support for runtime, gateway integration, identity management, and agent memory, the AgentCore MCP server is purpose-built to accelerate the creation of Bedrock AgentCore-compatible components. You can use the AgentCore MCP server for rapid prototyping, production AI solutions, or for scaling your agent infrastructure.
Another update
Here are some other news and blog posts that caught my eye:
- AWS Builder ID now supports Google Sign In – You can now create an AWS Builder ID using Google Sign In. An AWS Builder ID is a personal profile that provides access to AWS applications including Kiro, AWS Builder Center, AWS Training and Certification, AWS re:Post, and AWS Startups.
- AWS API MCP Server v1.0.0 Release – The AWS API MCP server acts as a bridge between AI assistants and AWS services, allowing underlying models to interact with any AWS API through natural language by creating and executing syntactically correct CLI commands. The AWS API MCP Server is open-source and is now available on the AWS Labs GitHub repository.
- AWS Knowledge MCP Server Now Generally Available – AWS Knowledge Server provides AI agents and MCP clients with access to authoritative knowledge, including documentation, blog posts, What’s New announcements, and well-crafted best practices, in an LLM-compatible format. With this release, the server also includes knowledge of the regional availability of AWS APIs and CloudFormation resources.
- AWS Transform Now Enables Terraform for VMware Network Automation – AWS Transform now offers Terraform as another option for automatically generating network infrastructure code from VMware. The service translates your source network definitions into reusable Terraform modules that complement current AWS CloudFormation and AWS Cloud Development Kit (CDK) support.
Upcoming AWS events
Check your calendar and sign up for upcoming AWS events:
- AWS AI Agent Global Hackathon – This is your chance to dive deep into our powerful generative AI and build something truly amazing. From September 8th to October 20th, you have the opportunity to build AI agents using the AWS AI Services Suite, compete for over $45,000 in prizes and exclusive launch opportunities.
- AWS Gen AI Lofts – You can learn AWS AI products and services in exclusive sessions, meet industry leaders, and gain valuable networking opportunities with investors and peers. Register in your nearest city: Paris (October 7-21), London (October 13-21) and Tel Aviv (November 11-19).
- AWS Community Days – Join community conferences that include technical discussions, workshops, and hands-on labs led by AWS expert users and industry leaders from around the world: Munich (October 7), Budapest (October 16).
You can browse all upcoming AWS events and AWS launch events.
That’s it for this week. Check back next Monday for another weekly recap!
— Prasad