Experience · Software component

Layered Explanation View

Software componentExperienceExperience & Human OversightVariation point (abstract)arc:LayeredExplanationView

An abstract presentation tier that renders one agent decision at a disclosure depth matched to a stakeholder persona's expertise, information needs and decision stakes.

Responsibility. Presents a decision explanation at the depth appropriate for one stakeholder tier.

Also known as: Layered transparency architecture, Perspective-specific view, Persona-specific explanation view

Direct neighbourhood (hover for relationship types)

Variants

Variant	When to choose
Exhaustive Audit Explanation View	Choose for expert analysts and compliance or regulatory auditors conducting deep audits or fairness reviews of high-stakes decisions.
Intermediate Explanation View	Choose for regular users with moderate expertise (loan officers, credit analysts, moderators) and medium-stakes decisions: key factors, feature weights, confidence, comparisons and governing thresholds.
Summary Explanation View	Choose for novice users, customers and affected parties, and for routine low-stakes decisions: plain-language summary of primary factors with actionable improvement or recourse guidance.

Relationships

reads dependency

Trace Store Ch10.5

is routed to by dynamic

Explanation Presenter Ch10.5

Design guidance

SHOULD identify and segment stakeholder personas (developers, business, regulators, affected parties, customers) upfront rather than adapting after confusion arises.
Detail hidden by default MUST remain accessible to those who need it; hiding complexity is not eliminating it.
SHOULD switch view automatically on detected user role without manual configuration.

Classification

Patterns: Layered transparencyRole-based adaptationStakes-based display strategyProgressive disclosure
Quality attributes: Transparency and accountability (NIST AI RMF: accountable and transparent)Interaction capability (ISO/IEC 25010)Explainability (NIST AI RMF: explainable and interpretable)
Risks mitigated: Cognitive overloadOne-size-fits-all explanations that satisfy no oneInappropriate information disclosure

Sources

Ch10.5: T. Nguyen, "Human-over-the-Loop," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 10.5. ISBN: 9798244538229.