Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Strands

AI overview

Sign in and the AI will write an overview from our coverage.

Headlines · 4

  1. AWS Adds a Hands-On Multi-Turn RL Guide for SageMaker AI

    AWS Machine Learning Blog published an end-to-end guide to multi-turn reinforcement learning (MTRL) on Amazon SageMaker AI, covering agent deployment, dataset preparation, training, MLflow monitoring and evaluation at serving settings. The workflow trains a policy using a reward for the outcome of an entire multi-step episode, without requiring the correct action trajectory, and supports agents hosted on Bedrock AgentCore or customer infrastructure. In AWS’s Wordle example, the company reports that gpt-oss-20b improved from 61% to 84% solve rate at default reasoning effort and from 15% to 69% at its trained low-effort setting, costing about $339 in training tokens.

    AWS Machine Learning Blog · 🔥 0
  2. AWS Agent Registry enables runtime tool discovery for AI agents

    AWS Agent Registry is generally available as a managed catalog for discovering MCP servers, agents, and agent skills. Orchestrators can use hybrid keyword and semantic search to find approved, discoverable records, then instantiate request-scoped clients from their protocol descriptors. Registry search results do not include invocation credentials, which applications must obtain through a separate trusted configuration path.

    AWS Machine Learning Blog · 🔥 0
  3. AWS recaps September Bedrock, AgentCore and Strands updates

    An AWS Machine Learning Blog recap says Amazon Bedrock added several capabilities for AI builders in September: Amazon Bedrock Managed Agents powered by OpenAI is now in public preview, and the AgentCore runtime has lower cold-start latency and scales sessions to zero when idle. Strands introduced an open source agent harness that AWS says matches popular harnesses on accuracy while using 28 percent fewer tokens, plus Strands Decider 2B, an open source 2B-parameter decision model that returns answers locally in about 115ms. Bedrock also lists OpenAI's GPT-6 Astra, Sol and Luna, along with Claude Fable 5.1, Claude Opus 5.5, Claude Sonnet 5.5, Moonshot AI's Kimi K3 and xAI's Grok 4.6 and 4.7, and added native ServiceNow, Salesforce and Zendesk connectors to its managed knowledge base.

    AWS Machine Learning Blog · 🔥 0
  4. One prompt hijacked every AgentCore agent in an AWS account, Zenity says

    Security firm Zenity Labs published research on a vulnerability chain it calls "AgentCorruption": chat access to a single public Amazon Bedrock AgentCore agent was enough to trick it, in plain language, into querying the instance metadata service at 169.254.169.254 and sending its own temporary AWS credentials to an external server. Using AgentCore's overly broad default execution role, the researchers then listed and invoked every agent in the same account and region, downloaded their source code and container images, read private user-agent conversations and secrets from AWS Secrets Manager, and poisoned long-term memory to make the hijack persistent. Zenity says it reported the findings to AWS on 25 December 2025; AWS has since made IMDSv2 the default for new AgentCore deployments and narrowed the default role.

    The Decoder · 🔥 0

Experience and discussion from the community

Share my Strands experienceAsk about Strands

Nobody has shared their experience with Strands yet.