Cognition · Software component
Decision Explainer
Software componentCognitionCognition & MemoryVariation point (abstract)arc:DecisionExplainer
An abstract explanation component that generates a justification for a specific agent or model decision in terms understandable to its audience.
Responsibility. Derives why a particular decision was made from the decision's inputs and model behaviour.
Also known as: Explanation technique
Variants
| Variant | When to choose |
|---|---|
| Counterfactual Explainer | Choose when users need to know the minimal changes that would flip the decision (why-not / recourse). |
| Decision Factor Explainer | Choose when users need the key factors behind a decision and their relative importance. |
| Example-Based Explainer | Choose when comparing the case to k similar past decisions conveys the rationale better than factor weights. |
| Local Surrogate Explainer | Choose when the decision model is opaque and a model-agnostic local approximation of top feature contributions is needed. |
Relationships
is invoked by dependency
reads dependency
is evaluated by assurance
Design guidance
- MUST tie explanations to real system logic and verify them with fidelity testing (Ref10.02).
- SHOULD offer multiple explanation types (Ref10.02).
Classification
- Patterns
- Explainable AI
- Quality attributes
- Explainability (NIST AI RMF: explainable and interpretable)Interaction capability (ISO/IEC 25010)Transparency and accountability (NIST AI RMF: accountable and transparent)
- Risks mitigated
- Black-box perceptionPost-hoc rationalization
Sources
- Ch10.1: T. Nguyen, "Conversational UI," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 10.1. ISBN: 9798244538229.
- Ref10.02: "Explainability and Interpretability in Agent Systems," unpublished reference note (02-Explainability-Interpretability.md), Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam supplementary materials, 2026. unpublished note