> For the complete documentation index, see [llms.txt](https://developer.harness.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://developer.harness.io/ai-evals/guides.md).

# Guides

- [Multi-Turn & Agentic Evals](https://developer.harness.io/ai-evals/guides/overview.md): Evaluate multi-turn conversations and agentic systems, including HITL scripts and tool-use trajectories.
- [Observability and Analytics](https://developer.harness.io/ai-evals/guides/overview-1.md): Inspect production traces, promote real interactions to datasets, and track pass-rate trends across evals and suites.
- [Pipeline Integration](https://developer.harness.io/ai-evals/guides/overview-2.md): Add AI Evals to Harness pipelines to gate deployments on evaluation results.
- [SDK Reference](https://developer.harness.io/ai-evals/guides/overview-3.md): Reference documentation for the harness-evals Python SDK.
- [Tutorials](https://developer.harness.io/ai-evals/guides/overview-4.md): End-to-end tutorials that walk through real evaluation scenarios with Harness AI Evals.