AI · Governance
AI policies
Thresholds, routing, escalation, model selection · last updated by Sam Hagen on 2026-05-02
Active policies
24
across thresholds, routing, escalation, models
Confidence threshold
Medium · 0.70
global default · per-policy overrides allowed
Auto-escalations
8
per week · trailing avg
Models in use
4
Opus 4.7 · Sonnet 4.6 · Sonnet 4.6 (vision) · Haiku 4.5
- Risk flag confidence at 0.70 is producing 23% false positives this month — consider raising to 0.75.
- Brief auto-categorization confidence threshold of 0.65 means 1 in 8 intakes still goes to human review — within target.
AI grounded in last 30 days of policy outcomes
Risk flag confidence threshold
Minimum AI confidence required before an event is flagged as at-risk
Lower threshold = more flags surfaced. Higher = fewer false positives.
Outlier detection sensitivity
Standard deviations from category baseline before a charge or proposal item is flagged unusual
Vendor recommendation minimum rating
Vendors below this rating won't be auto-recommended
Brief auto-categorization confidence
Below this, intake brief is routed to human reviewer
Anomaly cluster minimum count
Minimum occurrences before AI surfaces a cross-event pattern
AI flags, doesn’t fix · every threshold change is logged and reversible · 24 active policies govern the system