What are LLM guardrails?

Guardrails are checks applied to AI requests and responses to block or change content that breaks a policy. Typical rules detect personal data, secrets, prompt injection, and unsafe topics. Running them in a gateway applies the same rules to every model and application instead of rebuilding them in each codebase.

Also called: LLM guardrails, AI guardrails · Last updated

Where they run

Input guardrails inspect a prompt before it reaches a provider. Output guardrails inspect the response before it reaches the user. A rule can block the request, redact the matching text, or only record the event.

Guardrails on LLM Gateway

Built-in content guardrails are part of the Enterprise plan.

Learn more

Related terms