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 in this course will gain the ability to diagnose AI agent failures quickly using the Strands Evals SDK's detector functions. They will learn to interpret structured output -- including categorized failures with confidence scores, causal chains linking root causes to symptoms, and fix recommendations indicating whether changes belong in system prompts or tool definitions. The course also covers integrating detection into evaluation pipelines for automated diagnosis on every test run, reducing diagnosis time from hours to minutes and moving beyond simple scores to understand why agents fail and how to fix them.
