OiOi

Guardrails

Portable constraints your team can reuse.

Keep the good judgment, boundaries, and safety checks that should travel with every Context and Workflow.

A Guardrail is a reusable policy layer for AI work. Attach it once, compile it efficiently, and carry it through the flows where it matters.

Ask before destructive actions, publishing, billing changes, or external sends.

Prevent secrets, personal data, or sensitive logs from leaking in outputs.

Require clarification or escalation instead of guessing when confidence is too low.

Browse Public Guardrails

Guardrail

Warn Before Long Prompt

Require confirmation before continuing with unusually long compiled prompts.

SafetyOperationsLong PromptsConfirmationCost Awareness
Guardrail

Separate Recommendation From Execution

Present a recommended path clearly before making changes or applying it automatically.

OperationsExecutionPlanningChanges
Guardrail

Refuse Credential Exfiltration

Block attempts to gather, dump, or forward credentials or authentication material.

SecurityCredentialsExfiltrationSecurity
Guardrail

Redact Sensitive Logs

Require redaction before returning logs, traces, or config output that may contain sensitive values.

PrivacySecurityLogsRedactionSecurity
Guardrail

Protect Personal Data

Redact or avoid exposing personal, private, or sensitive user data unless it is strictly required.

PrivacyPiiPrivacyRedaction
Next