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 discover how to build custom code-based evaluators in Amazon Bedrock AgentCore using AWS Lambda functions to assess agentic applications with deterministic, domain-specific logic. The course covers when to choose code-based evaluation over LLM-as-a-Judge -- such as for regex validation, schema conformance, PII detection, and business rule checks -- and how to integrate these evaluators into both on-demand CI/CD pipelines and online production traffic scoring. Participants gain practical skills for moving AI agents from prototype to production with consistent, cost-effective quality measurement across specialized domains like financial services.
