Agentic AI Reference Architecture

Safety & Security · Data artifact

Blocking Violation Response Policy

Data artifactSafety & SecuritySafety, Security & Governancearc:BlockingViolationResponsePolicy

A violation response policy that blocks the output and returns a standardized, polite refusal (hard or softened with explanation).

Responsibility. Refuses and withholds violating outputs.

Also known as: Hard refusal, Softened refusal with explanation

Variant of Violation Response Policy abstract

When to choose. Choose for clearly prohibited categories (e.g., illegal activity) where erring on the side of safety outweighs refusing some acceptable requests.

specializesalternative toalternative toalternative toalternative toViolation Response Policy: specializesViolation Response PolicyHuman-Escalation Violation Response Policy: alternative toHuman-Escalation Violati…Content-Modification Violation Response Policy: alternative toContent-Modification Vio…Warning-Label Violation Response Policy: alternative toWarning-Label Violation …Monitor-Only Violation Response Policy: alternative toMonitor-Only Violation R…
Direct neighbourhood (hover for relationship types)

Relationships

alternative to variability

Classification

Risks mitigated
Delivery of prohibited content

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. 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.
  3. Ref9.01: "AI Safety Frameworks for Agent Systems," unpublished reference note (01-AI-Safety-Frameworks.md), Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam supplementary materials, 2026. unpublished note