> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/guardrails/v0.24.1/evaluation/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/guardrails/_mcp/server.

# Evaluation

## Docs

- [Evaluate Configuration](https://docs.nvidia.com/nemo/guardrails/v0.24.1/evaluation/evaluate-configuration.md): Evaluate a guardrails configuration with policies, interactions, LLM-as-a-judge checks, and the Eval UI.
- [Evaluation Methodology](https://docs.nvidia.com/nemo/guardrails/v0.24.1/evaluation/evaluation-methodology.md): Design policy-based evaluation datasets and interpret compliance results for guardrails configurations.
- [Evaluate NeMo Guardrails Library Performance](https://docs.nvidia.com/nemo/guardrails/v0.24.1/evaluation/evaluate-guardrails.md): Measure accuracy and performance of dialog, fact-checking, moderation, and hallucination rails.
- [LLM Vulnerability Scanning](https://docs.nvidia.com/nemo/guardrails/v0.24.1/evaluation/llm-vulnerability-scanning.md): Scan LLM applications for vulnerabilities using Garak and measure guardrails protection rates.