Guardrail Rules | AI Router

Configure guardrail rules in the AI Router to validate and control LLM requests and responses with evaluators triggered by CEL conditions.

Feature available with the Enterprise Plan

Guardrail Rules define conditions under which evaluators are applied to requests passing through the AI Router. A guardrail is only triggered when its rule conditions are matched, not on every request.

Use cases

Guardrail rules are most useful when the same safety or compliance check needs to apply consistently across many requests.

Add jailbreak protection to all customer-facing banking traffic

Runs a jailbreak detection Evaluator on all customer-facing requests at the router level, adding an extra security layer across AI Router traffic.

Enforce GDPR PII checks across the entire workspace

Enforces GDPR compliance by running PII detection on all matching requests workspace-wide from a single rule.

Validate customer detail access for the sales team

Validates customer detail access for the sales team by calling an external Evaluator on every matching request before it reaches the model.

Monitor tone of voice across all company traffic

Applies a tone of voice Evaluator at the router level so every response is checked against the company’s tone guidelines.

Apply EU AI Act compliance checks to EU-routed requests

Runs a compliance Evaluator on EU-routed requests only, scoped using the Rule Builder so the guardrail applies exactly where it is needed without affecting other traffic.

Run safety and quality checks on targeted traffic using metadata

Runs jailbreak detection and response relevance Evaluators at 50% sample rate each, scoped to specific traffic using a metadata condition in the Rule Builder.

Visibility

• Global rules: visible to workspace administrators only.
• Project rules: visible to all members of the scoped project.

Creating a guardrail rule

From the Guardrail Rules list, click Add New Rule. A panel opens on the right with the following fields.

General

Field	Description
Rule Name	A display name for the guardrail rule.
Description	Optional context for administrators.
Enable Rule	Toggle to activate or deactivate the rule. When enabled, the rule is active and applied to matching requests.

Evaluators

Select the Evaluators to run when this rule is triggered. Click Add to attach one or more evaluators from the scoped project.

Execution settings

Field	Description
Timeout	Maximum time in seconds allowed for the guardrail to complete. If the timeout is reached, the guardrail is skipped.

Rule Builder

The Rule Builder constructs the match conditions that determine when the guardrail is triggered. Clicking Add opens a dropdown with the following condition types:

Condition	Description
Header	Match on a request header name and value.
Model	Match on the model being called.
Identity	Match on the identity making the request.
Metadata	Match on metadata attached to the request.
Project	Match on the project scope of the request.

You can also click Add group to nest conditions into a logical group. Multiple conditions within a group are joined with and. Groups themselves can be joined with either and or or. Select the operator between groups to control how they combine. Each condition can be removed with .

The builder generates a CEL (Common Expression Language) expression shown read-only in the CEL Expression Preview below. The guardrail is only triggered when the expression evaluates to true.