---
title: "Protect agents | Grafana Cloud documentation"
description: "Configure guards and redact sensitive content from agent requests."
---

> For a curated documentation index, see [llms.txt](/llms.txt). For the complete documentation index, see [llms-full.txt](/llms-full.txt).

# Protect agents

Use guards to check requests before they reach the model and redaction to remove sensitive content.

- [Set up guards](/docs/grafana-cloud/observe-and-act/agent-observability/protect-agents/guards) to block, redact, or filter requests.
- [Redact PII and secrets](/docs/grafana-cloud/observe-and-act/agent-observability/privacy-and-access/pii-and-secrets-redaction) to configure SDK and server-side redaction and review their coverage and limits.

Before you send data, refer to [Data handling and privacy](/docs/grafana-cloud/observe-and-act/agent-observability/privacy-and-access/privacy) for capture controls, retention, and residency. These settings complement the request controls in this section.

- [Set up guards](/docs/grafana-cloud/observe-and-act/agent-observability/protect-agents/guards/)  
  Configure guards to block, redact, or filter LLM requests before they reach the model.

## Next steps

- [Browse and debug conversations](/docs/grafana-cloud/observe-and-act/agent-observability/observe-and-troubleshoot/conversations)
- [Review privacy and access](/docs/grafana-cloud/observe-and-act/agent-observability/privacy-and-access)