{"id":"rhoai-guardrails-safety-layer","text":"Guardrails is the OpenShift AI safety mechanism for filtering model input and output on deployed models.","truth_value":"IN","source":"entries/2026/03/05/en-documentation-red_hat_openshift_ai_self-managed-223.md","source_url":"","source_hash":"9b0e86184307a603","justifications":[],"dependents":[],"metadata":{},"explanation":{"steps":[{"node":"rhoai-guardrails-safety-layer","truth_value":"IN","reason":"premise"}]}}