Use cases
Examples of common evaluation use cases
This section includes use case guides for a few common evaluation scenarios.
- JSON evaluations: Validate JSON outputs from LLMs.
- RAG evaluations: Verify LLM outputs end-to-end performance testing.
- AI agent evaluations: Avoid unreliable reasoning, inconsistent data, and hallucinations.
See each guide for a complete walk through.
Updated 12 days ago