Agentic AI Reference Architecture

Safety & Security · Data artifact

Warning-Label Violation Response Policy

Data artifactSafety & SecuritySafety, Security & Governancearc:WarningLabelViolationResponsePolicy

A violation response policy that delivers the output with warnings or disclaimers attached, such as misinformation warnings, confidence disclaimers or 'consult a professional' notices.

Responsibility. Flags questionable outputs with warnings instead of blocking.

Also known as: Disclaimer injection

Variant of Violation Response Policy abstract

When to choose. Choose when preserving user autonomy matters and the concern (e.g., possible misinformation, low confidence) warrants flagging rather than blocking.

specializesis target of alternativeTois target of alternativeTois target of alternativeToViolation Response Policy: specializesViolation Response PolicyBlocking Violation Response Policy: is target of alternativeToBlocking Violation Respo…Human-Escalation Violation Response Policy: is target of alternativeToHuman-Escalation Violati…Content-Modification Violation Response Policy: is target of alternativeToContent-Modification Vio…
Direct neighbourhood (hover for relationship types)

Relationships

alternative to variability

Sources

  1. Ch9.5: T. Nguyen, "Constitutional AI," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 9.5. ISBN: 9798244538229.
  2. Ref9.01: "AI Safety Frameworks for Agent Systems," unpublished reference note (01-AI-Safety-Frameworks.md), Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam supplementary materials, 2026. unpublished note