|
|
Last week, the Anthropic Claude Sonet 4.5-best coding model in the world according to the SWE-Bench-Byl available in the Amazon Q Command Line (CLI) and Kiro. I’m excited about it for two reasons:
First, a few weeks ago I spent 4 intensive days with a global customer who supplied a development workshop with the help of Ai-Asisted, where I experienced first-hand, as Amazon Q Cli increases the productivity of the developer. 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 take them for at least a few weeks. With Claude Sonnet 4.5 Anthropic in Amazon Q Cli, I know that developer productivity will be further improved.
Secondly, I started to prepare for my code conversation at AWS Re: Invent 2025, where my fellowly and I will show live coding to modernize the older code base using Kiro. I can’t wait to use Anthropic’s Claude Sonnet 4.5 in Kiro to create a living demo. If you want to see this demo and more than a thousand other cloud and AI sessions, join us at AWS Re: Invent 2025 in Las Vegas from 1 – 5 December.
Start of Last Week
Here are a few launches that caught me:
- Available Claude Sonnet 4.5 in Amazon Bedrock – the most intelligent model Anthropic, the best for coding and complex agents, is now available in Amazon Bedrock. Using Claude Sonnet 4.5 in Amazon Bedrock, developers get access to a fully managed service that not only provides a unified API for endowment models (FMS), but keeps its data under complete control using tools for security and optimization.
- AWS Outpostics support third-party third-party storage integration with Dell and HPE-AWS Outposts Integration of third-party storage includes Dell PowerStore and HPE Alletra Storage MP B10000, connecting an existing integration with NetAPP-Prumes Enterprise Storagerary Arara. This integration serves three key purposes. First of all, it will help you keep your existing storage infrastructure in migration of VMware workload to AWS. Second, it will help you meet strict data stay requirements by keeping your data on the use of AWS services. Thirdly, this means that you can use AWS bases with third -party storage fields via AWS tools.
- Amazon ECS managed instances are now available – AMAZON ECS managed instances for containerized applications are a new fully managed computing option for AMAZON ECS designed to eliminate overheads for infrastructure management while allowing you to access full AMAZON EC2. Instances managed by ECS will help you start quickly and scalance your workload while increasing performance and lowering the total cost of ownership.
- Applications map is now generally available for Amazon Cloudwatch-amazon Cloudwatch now helps you track extensive distributed applications by automatically discovering and organizing services on the basis of configurations and their relationships. With this new application performance monitoring (APM), you can quickly visualize which applications and addictions are focused on solving problems with distributed applications.
- The Amazon Bedrock Agentcore Model Context Protocol (MCP) is now available-SE-built-in support for running, integrating gateway, management and memory of agents is AgentCore MCP server purpose to speed up components compatible components. You can use Agentcore MCP for quick prototyping, production AI solutions or for scaling Agent infrastructure.
Another update
Here are some other innovations and posts on the blog that seemed interesting to me:
- The AWS Builder now supports Google login – now you can create AWS Builder ID using Google login. 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.
- The ASP API API MCP Server V1.0.0 – ASS API MCP server acts as a bridge between AI Assistants and AWS Services, allowing endowment models to interact with any API API by creating and performing syntactically correct CLI commands. The API API API API is open-source and is now available in the AWS Labs Github.
- The AWS Knowledge MCP server is now generally available to-server AWS Knowledge Server provides AI agents and MCP clients access authoritative knowledge, including documentation, blog posts, about the new notifications and well architected proven procedures, compatible with LLM. With this publication, the server also includes knowledge of the regional availability of APS API and Cloudformation Resources.
- The AWS Transform now allows Terraform to automate VMware – AWS Transform now offers Terraform as another option to automatically generate network infrastructure code from VMware. The service converts the definition of your source network to repeatedly usable Terraform modules, complements the current AWS Cloudformation and AWS Cloud Development Kit (CDK) support.
Upcoming AWS events
Check your calendar and register for the upcoming AWS events:
- Agent AI AI Global Hackathon – This is your chance to dive deep into our powerful generative AI and create something really amazing. From September 8 to October 8, you have the opportunity to create AI agents using AWS Suite of AI Services, compete for more than $ 45,000 in prices and exclusive market opportunities.
- You can learn AWs AI products and services with exclusive sessions, meet the leading experts on industry and have valuable opportunities to create networks with investors and peers. Register in your nearest town: Paris (7 – 21 October), London (13 – October 21) and Tel Aviv (11 – 19 November).
- Community of AWS Community Days-Conferences of communities containing technical discussions, workshops and practical laboratories led by AWS professional users and industry leaders from all over the world: Munich (October 7), Budapest (October 16).
You can browse all upcoming AWS events and AWS startup.
That’s all for this week. See the next Monday for the next week round!
– a pig