Agentic AI Reference Architecture

Cognition · Software component

Example-Based Explainer

Software componentCognitionCognition & Memoryarc:ExampleBasedExplainer

A decision explainer that justifies a decision by retrieving the most similar historical cases and their outcomes.

Responsibility. Explains a decision by analogy to similar past decisions.

Also known as: Similar-case explanation

Variant of Decision Explainer abstract

When to choose. Choose when comparing the case to k similar past decisions conveys the rationale better than factor weights.

is target of alternativeTois target of alternativeToreadsspecializesalternative toCounterfactual Explainer: is target of alternativeToCounterfactual ExplainerDecision Factor Explainer: is target of alternativeToDecision Factor ExplainerDecision Outcome History Store: readsDecision Outcome History…Decision Explainer: specializesDecision ExplainerLocal Surrogate Explainer: alternative toLocal Surrogate Explainer
Direct neighbourhood (hover for relationship types)

Relationships

reads dependency

alternative to variability

Classification

Patterns
Example-based explanation
Quality attributes
Explainability (NIST AI RMF: explainable and interpretable)

Sources

  1. Ref10.02: "Explainability and Interpretability in Agent Systems," unpublished reference note (02-Explainability-Interpretability.md), Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam supplementary materials, 2026. unpublished note