Evaluating and troubleshooting generative AI applications
Use Bedrock model evaluation, RAG evaluation and LLM-as-a-judge, then diagnose bad retrieval, hallucinations, truncation and throttling.
This lesson is part of full AIP-C01 access
The first 2 AIP-C01 lessons are free. Full access opens every lesson with its practice questions, and the exam-style AIP-C01 question bank.
In this lesson- Amazon Bedrock evaluations
- Testing practice
- Find the failing layer
- Observability
- Exam traps
- Practice questions