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
- 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-flagged events
- Trigger
- Event status flips to at-riskorblocked
- Routes to
- Producer (primary), Account Lead (cc), notification at T-24h before next standup
- Override available
- Yes
Vendor proposal outliers
- Trigger
- Proposal item flagged unusualormissing
- Routes to
- Producer + Sourcing (Tier 2producer for >$50K)
Approval requests
Failing
- Trigger
- Submitted via
/approvalsor in event detail - Routes to
- Designated approver per role × scope matrix; falls back to team lead if approver unavailable >24h
Currently failing — Slack OAuth expired.
/admin/integrationsContract anomaly
- Trigger
- Contract revision touches a flagged clause
- Routes to
- Account Lead + Legal (cc)
AI flags, doesn’t fix · every threshold change is logged and reversible · 24 active policies govern the system