Experience · Software component
Proactive Explanation Expander
Software componentExperienceExperience & Human Oversightarc:ProactiveExplanationExpander
An expansion controller that automatically opens detailed explanation layers, or shows guided hints, when confidence is low, outcomes are unexpected, decisions deviate from history, or stakes are high.
Responsibility. Automatically surfaces detailed explanations when risk signals warrant them.
Also known as: Intelligent expansion, Guided disclosure, Automatic escalation of explanation depth, Adaptive disclosure
Variant of Explanation Expansion Controller abstract
When to choose. Choose when confidence may fall below thresholds, decisions may deviate from historical patterns, or high-stakes scenarios arise, so critical detail must surface without user initiative.
Relationships
reads dependency
receives data from dynamic
alternative to variability
Design guidance
- SHOULD automatically expand when confidence falls below established thresholds, decisions deviate from historical patterns, or high-stakes scenarios emerge.
- SHOULD provide contextual hints stating what deeper layers contain and when they might change the user's assessment.
- High-confidence straightforward cases SHOULD receive minimal explanation (e.g., a simple green indicator).
Classification
- Patterns
- Proactive explanationGuided disclosure hintsConfidence-based escalation
- Quality attributes
- Transparency and accountability (NIST AI RMF: accountable and transparent)Safety (ISO/IEC 25010 | NIST AI RMF: safe)
- Risks mitigated
- Undiscovered critical explanationsSelective disclosure and cherry-pickingWorkflow bottlenecks from explaining every case
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.