Urgent.News

What's breaking now, across thousands of outlets.

AI

Amazon Bedrock AgentCore harness adds Strands harness defaults, built-in tools, and lifecycle hooks

Amazon Bedrock AgentCore harness now runs on the open-source Strands harness, bringing a recommended model, task-oriented defaults, automatic prompt caching, proactive context management, and new built-in tools. It also adds lifecycle hooks so you can run deterministic allow or deny checks at defined points in the agent loop.

Amazon Bedrock AgentCore harness has been upgraded to use Strands harness, an open-source agent harness released earlier this year under an Apache 2.0 license. The enhanced harness introduces lifecycle hooks, enabling deterministic checks and notifications at defined points in the agent loop. Agents that rely on managed defaults now receive a recommended model, a task-oriented system prompt, automatic prompt caching for Anthropic models, and proactive context management.

Built-in tools for planning, web retrieval, filesystem access, context offloading, and task delegation have also been added. These features empower agents to handle long tasks more efficiently, manage subtasks, reduce context window usage, and delegate work when necessary. The upgrade does not require any new resources or integrations; agents already using AgentCore harness will automatically receive both updates.

Strands capabilities provide an assembled agent foundation with recommended instructions, tools, and context management, while Amazon Bedrock AgentCore harness operates this foundation as a managed AWS service. Secure, kernel-isolated microVMs are used for each session, ensuring high availability and managed compute, scaling, and memory within Amazon Bedrock AgentCore.

Agents retain control over model, instructions, tools, permissions, and lifecycle policies while the underlying execution environment is managed by AgentCore.

Written by urgent.news from AWS Machine Learning's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

This story

This is one outlet's version. Read the fullest account.

Every outlet that reported this, and when →

Read the original at aws.amazon.com →

More in AI

More from Thursday 19 November →