Violation Response Policy

Data artifactSafety & SecuritySafety, Security & GovernanceVariation point (abstract)arc:ViolationResponsePolicy

An abstract configuration stating what the system does when an output is judged to violate, or plausibly violate, a principle.

Responsibility. Determines the system's reaction to principle violations.

Also known as: Failure response policy, Enforcement strictness

Direct neighbourhood (hover for relationship types)

Variants

Variant	When to choose
Blocking Violation Response Policy	Choose for clearly prohibited categories (e.g., illegal activity) where erring on the side of safety outweighs refusing some acceptable requests.
Content-Modification Violation Response Policy	Choose when the violating portion can be removed or rewritten so the remaining response stays useful.
Human-Escalation Violation Response Policy	Choose for ambiguous cases with possible legitimate justification (fiction, security research) or high-stakes dilemmas, accepting slower responses for greater accuracy.
Monitor-Only Violation Response Policy	Choose for borderline outputs approaching policy boundaries where immediate blocking is not required; use blocking mode for inviolable legal, ethical or safety constraints.
Warning-Label Violation Response Policy	Choose when preserving user autonomy matters and the concern (e.g., possible misinformation, low confidence) warrants flagging rather than blocking.

SHOULD be chosen explicitly as a judgment balancing user experience, autonomy and safety assurance.

Quality attributes: Safety (ISO/IEC 25010 | NIST AI RMF: safe)Interaction capability (ISO/IEC 25010)

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.
Ch10.4: T. Nguyen, "Human-in-the-Loop," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 10.4. ISBN: 9798244538229.