利用 Bedrock AgentCore 与 GitHub Actions 实现 agent 自动化评估
原标题：Automated agent evaluation with Amazon Bedrock AgentCore and GitHub Actions
AI 摘要
AWS 博客介绍了如何使用 Amazon Bedrock AgentCore 和 GitHub Actions 构建自动化 agent 评估的 CI/CD 质量门禁。该方案通过 CDK 部署 agent 和 MCP 服务器，利用 AgentCore Evaluate API 对 agent 响应进行评分，并在评分下降时阻止 PR 合并。文章详细说明了 OAuth 认证、角色权限控制以及三种评估模式（按需、在线、批量）的实现。
正文节选
Automated agent evaluation with Amazon Bedrock AgentCore and GitHub Actions Build a continuous integration and continuous delivery (CI/CD) quality gate that deploys an agent with role-based MCP tools, evaluates it, and blocks PRs when evaluation scores drop. You shipped an AI agent on Amazon Bedrock AgentCore runtime. It calls tools through an MCP server protected by OAuth. Now you want CI to tell you when a code change makes its performance worse before it reaches production. This post walks th