Override Feedback Record

Data artifactHuman OversightExperience & Human Oversightarc:OverrideFeedbackRecord

A structured record of a human override of an agent decision capturing business context, the reviewer's reasoning for disagreeing, before-and-after outputs, and the reviewer's confidence in their own judgment.

Responsibility. Preserves the rationale of human corrections as a learning signal.

Also known as: Structured correction feedback

Direct neighbourhood (hover for relationship types)

Relationships

is read by dependency

is written by dependency

Feedback Collector abstract Ch10.5

Design guidance

SHOULD capture why a change was necessary, not just what changed, to separate systemic weaknesses needing retraining from isolated edge cases.

Classification

Patterns: RLHFHuman corrections as training signal
Quality attributes: Interaction capability (ISO/IEC 25010)Transparency and accountability (NIST AI RMF: accountable and transparent)
Risks mitigated: Treating overrides as isolated fixesConfusing systemic weaknesses with isolated edge cases

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.