From the source
Lead story
Ask your AI
Top stories
Models & availability
Latest
Amazon· Bedrock / NovaAutomated agent evaluation with Amazon Bedrock AgentCore and GitHub Actions
CI/CD quality gate blocks PRs when agent evaluation scores drop below threshold.
Amazon Bedrock AgentCore now supports automated agent evaluation through a GitHub Actions pipeline that deploys an agent, runs evaluation prompts via the AgentCore Evaluate API, and blocks pull requests when evaluation scores drop.
The post describes a reference implementation using CDK, role-based MCP tools, and OAuth-protected runtimes.
From the source
This post walks through a GitHub Actions pipeline that deploys an agent to AgentCore runtime and evaluates the agent with evaluation prompts using the AgentCore Evaluate API.
aws.amazon.com
Other stories
Amazon · 2 OctSweep thousands of leases for compliance using Amazon Quick and the Adjudicated Query patternAmazon · 2 OctAdd secure Web Search to Claude Desktop with Amazon Bedrock AgentCoreAmazon · 2 OctFine-tune a search agent with multi-turn RL on Amazon SageMaker AIAmazon · 1 OctServe live, governed data in AI-built apps with Amazon Quick