This course was developed by members of AWS Technical Field Communities (TFC), an AWS community of technical experts. The content is intended to complement our standard training curriculum and augment your AWS learning journey. We are aware some courses have accessibility limitations and are working to address. If you require accommodation, please contact AWS Training and Certification Customer Support.
Learners will gain hands-on experience building a CI/CD quality gate using Amazon Bedrock AgentCore and GitHub Actions. The course covers deploying a Strands agent with role-based MCP tools to AgentCore runtime via CDK, authenticating OAuth-protected runtimes from CI using machine-to-machine client credentials flow, running on-demand evaluations with the AgentCore Evaluate API, and enforcing automated merge gates that block pull requests when agent performance regresses. Participants will also learn a three-layer auth pattern with a shared Cognito pool and understand how to integrate LLM-as-a-judge evaluation into continuous delivery workflows for AI agents.
