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

Recommended adjustments
AI-flagged · producers decide
  • 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

Current0.70(Medium)· Allowed range 0.50 to 0.95

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

Current1.5σ· Allowed range 1.0 to 3.0

Vendor recommendation minimum rating

Vendors below this rating won't be auto-recommended

Current4.0of5.0

Brief auto-categorization confidence

Below this, intake brief is routed to human reviewer

Current0.65

Anomaly cluster minimum count

Minimum occurrences before AI surfaces a cross-event pattern

Current3events

AI flags, doesn’t fix · every threshold change is logged and reversible · 24 active policies govern the system