Updated
Guardrails & Validation
Protect agent runs with PII masking, tool approval, and model policies.
Last updated
Protect agent runs with PII masking, tool approval, and model policies.
Instructions guide an agent’s decisions. Guardrails enforce controls around its execution.
Guardrails protect sensitive data before model requests. They can also pause selected skills for user approval. Organization-level policies restrict approved model families and providers.
Open Manage Agent → Guardrails to manage the controls for an agent.
Preview. Guardrails is a Preview feature. Controls and labels may change.
Tool Execution Approval
Pauses selected skill calls until the user allows or denies them
Allowed LLM Families and Providers
Limits model requests to organization-approved models and providers
Sensitive Data Masking and Tool Execution Approval are toggleable per agent. Model policy guardrails are always enforced by the AI Gateway.
Open Manage Agent → Guardrails.
Turn on Sensitive Data Masking or Tool Execution Approval.
Select the gear in that row to define its coverage.
The Guardrails page lists each guardrail’s Name, Type, and Status. A toggle controls per-agent guardrails. An Always enforced badge marks organization-level model policies.
PII masking detects selected entities and tokenizes their values. The original value stays in a secure vault. A permitted downstream step can restore it when needed.
Choose a provider, then define the entity rule:
A Deny list masks only selected entity types.
An Allow list masks every type except selected entities.
Enable masking whenever the agent handles PII. Unselected entities reach the model in clear text.
Tokenization requires a compatible executor version. See PII masking for providers, entity types, and tokenization details.
Tool Execution Approval pauses an agent before it runs selected skills. The user can allow the call or deny it. When denied, the agent continues without that call.
Require approval for skills that access sensitive data or take external actions. You can select individual skills or require approval for every current and future skill.
See Tool execution for approval settings and the user experience.
The AI Gateway enforces the approved LLM families and providers for every model request. These guardrails are set by your organization. You can’t disable them per agent.
Guardrails — configure per-agent controls
PII masking — choose providers and masked entities
Tool execution — require approval before skills run
Last updated