> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://poly-ai.ferndocs.com/agent-studio/behavior/guardrails/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://poly-ai.ferndocs.com/_mcp/server.

# Guardrails

## Docs

- [Guardrails](https://poly-ai.ferndocs.com/agent-studio/behavior/guardrails/guardrails.md): Platform safety guardrails that protect your agent in production, with observability in conversation transcripts.
- [Safety filters](https://poly-ai.ferndocs.com/agent-studio/behavior/guardrails/safety-filters.md): Per-channel content filters that classify user input and agent output across hate, sexual, violence, and self-harm – and always-on jailbreak detection.