Experience · Data artifact
Intervention Threshold Policy
Data artifactExperienceExperience & Human Oversightarc:InterventionThresholdPolicy
A calibrated configuration of confidence and deviation thresholds separating actionable interventions requiring immediate response from informational notices and from signals that should not interrupt the user at all.
Responsibility. Defines when a signal is significant enough to warrant proactive intervention.
Also known as: Alert threshold calibration, Proactivity threshold
Relationships
configures structural
Design guidance
- SHOULD distinguish actionable alerts from informational notices.
- SHOULD NOT alert on minor deviations (e.g., every 1% variance from baseline); low thresholds train users to dismiss alerts reflexively.
Classification
- Risks mitigated
- Alert fatigue from overly sensitive thresholdsMissed genuine issues from overly high thresholds
Sources
- Ch10.2: T. Nguyen, "Proactive Agents," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 10.2. ISBN: 9798244538229.