Agentic AI Reference Architecture

Observability & Evaluation · Data artifact

Guardrail Test Suite

Data artifactObservability & EvaluationObservability & Evaluationarc:GuardrailTestSuite

A set of benign and adversarial test inputs paired with expected guardrail outcomes (blocked or answered) used to validate rails before deployment.

Responsibility. Defines expected guardrail behaviour for regression testing.

Also known as: Adversarial prompt set, Jailbreak, injection and extraction test cases

is read byis read byEvaluation Harness: is read byEvaluation HarnessAdversarial Robustness Evaluator: is read byAdversarial Robustness E…
Direct neighbourhood (hover for relationship types)

Relationships

is read by dependency

Sources

  1. Ch7.1B: T. Nguyen, "Nvidia NIM and Colang," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 7.1B. ISBN: 9798244538229.
  2. Ref7.03: NVIDIA, "Overview," NVIDIA NeMo Guardrails Library Developer Guide. Accessed: Sep. 27, 2026. [Online]. Available: https://docs.nvidia.com/nemo/guardrails/about-nemo-guardrails-library/overview
  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 Ref9.01: "AI Safety Frameworks for Agent Systems," unpublished reference note (01-AI-Safety-Frameworks.md), Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam supplementary materials, 2026. unpublished note