Skip to main content
AI Agents

Guardrails

Configure the agent's guardrails to moderate and protect its interactions with users.

Guardrails

The Guardrails page configures the safety filters applied to every message the agent sends and receives. Use them to block unsuitable content, protect sensitive data, and keep the agent inside the scope you intended.

Reach it through the Guardrails icon in the editor's side navigation.

Every setting saves itself and applies to the current working version.

The tabs

TabWhat it configures
GeneralTurning guardrails on, AI-assisted analysis, the blocked message
Harmful contentHate speech, insults, sexual content, violence and misconduct
Prompt attacksDetecting prompt injection and malicious manipulation
ProfanityImproper or offensive language
Contextual grounding checkAnswers with no basis in the context documents
Relevance checkAnswers outside the conversation's context
Denied topicsSpecific subjects the agent must not touch
Sensitive informationPersonal data (PII): mask it or block it

The General tab

Turn guardrails on

Enables or disables every guardrail on the agent. With it off, no filtering happens — the agent may return unsuitable or unsafe answers.

warning

Turning guardrails on increases the agent's response time, since every message is checked against the rules you defined.

Use AI to reinforce the guardrails

With this on, a language model reviews messages and answers to apply the guardrails in the more subjective or contextual cases — the ones deterministic filters cannot settle.

warning

This makes extra LLM calls on every interaction, increasing token consumption and the cost per conversation. It is only available with Turn guardrails on enabled.

The message for blocked prompts

The text shown to the user when a message is blocked by the guardrails. Use it to explain the agent's policies.