Experience · Software component
Confidence Indicator
Software componentExperienceExperience & Human Oversightarc:ConfidenceIndicator
A presentation component that renders decision confidence as contextualized visual scales (color gradients, gauges, ranges) with comparative context and plain statements of limitations instead of raw scores.
Responsibility. Displays contextualized decision confidence to users.
Also known as: Confidence display, Confidence metrics visualization, Color-coded confidence scale
Relationships
is invoked by dependency
reads dependency
receives data from dynamic
Design guidance
- SHOULD NOT present raw model confidence without context such as typical ranges and data limitations.
- SHOULD explicitly acknowledge limitations and recommend specialist review when confidence is moderate or low.
- SHOULD use the same confidence encoding consistently throughout the interface.
Quantitative guidance
As stated by the sources; verify before use.
- Example: '87% confidence—higher than 73% of cases reviewed this month' (Ch10.5).
- Example: moderate confidence 67% vs typical nodule-detection range 82–91% triggers specialist-review recommendation (Ch10.5).
Classification
- Patterns
- Contextualized confidenceComparative percentile contextTraffic-light confidence encoding
- Quality attributes
- Interaction capability (ISO/IEC 25010)Transparency and accountability (NIST AI RMF: accountable and transparent)
- Risks mitigated
- Confidence score misinterpretationFalse confidenceAutomation bias
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.