Category: Announcements

In this post, we go through how to use managed session storage to persist your agent’s filesystem state and how to execute shell commands directly in your agent’s environment.

In this post, we introduce Amazon Bedrock AgentCore Evaluations, a fully managed service for assessing AI agent performance across the development lifecycle. We walk through how the service measures agent accuracy across multiple quality dimensions. We explain the two evaluation approaches for development and production and share practical guidance for building agents you can deploy with confidence.

I’m excited to announce that AWS Security Agent on-demand penetration testing and AWS DevOps Agent are now generally available, representing a new class of AI capabilities we announced at re:Invent called frontier agents. These autonomous systems work independently to achieve goals, scale massively to tackle concurrent tasks, and run persistently for hours or days without constant human oversight. Together, these agents are changing the way we secure and operate software. In preview, customers and partners report that AWS Security Agent compresses penetration testing timelines from weeks to hours and the AWS DevOps Agent supports 3–5x faster incident resolution.

Traditional frameworks designed for static deployments cannot address the dynamic interactions that define agentic workloads. AI Risk Intelligence (AIRI), from AWS Generative AI Innovation Center, provides the automated rigor required to govern agents at enterprise scale—a fundamental reimagining of how security, operations, and governance work together systemically.

Today, we’re excited to announce that Amazon Bedrock is now available in the Asia Pacific (New Zealand) Region (ap-southeast-6). Customers in New Zealand can now access Anthropic Claude models (Claude Opus 4.5, Opus 4.6, Sonnet 4.5, Sonnet 4.6, and Haiku 4.5) and Amazon (Nova 2 Lite) models directly in the Auckland Region with cross region inference. In this post, we explore how cross-Region inference works from the New Zealand Region, the models available through geographic and global routing, and how to get started with your first API call. We

Today, we’re excited to announce the new Bidirectional Streaming API for Amazon Polly, enabling streamlined real-time text-to-speech (TTS) synthesis where you can start sending text and receiving audio simultaneously. This new API is built for conversational AI applications that generate text or audio incrementally, like responses from large language models (LLMs), where users must begin synthesizing audio before the full text is available.

In this post, we walk through the end-to-end workflow of using RFT on Amazon Bedrock with OpenAI-compatible APIs: from setting up authentication, to deploying a Lambda-based reward function, to kicking off a training job and running on-demand inference on your fine-tuned model.

This post explores the technical characteristics of the Nemotron 3 Super model and discusses potential application use cases. It also provides technical guidance to get started using this model for your generative AI applications within the Amazon Bedrock environment.

In this blog post, we introduce the concepts behind next-generation inference capabilities, including disaggregated serving, intelligent request scheduling, and expert parallelism. We discuss their benefits and walk through how you can implement them on Amazon SageMaker HyperPod EKS to achieve significant improvements in inference performance, resource utilization, and operational efficiency.

In this post, we explain how P-EAGLE works, how we integrated it into vLLM starting from v0.16.0 (PR#32887), and how to serve it with our pre-trained checkpoints.