# SCRIMED Intelligence Control Plane

Status: scrimed-intelligence-control-plane-active-synthetic-no-phi
Policy: scrimed-control-plane-policy-v2026-07-11

## Architecture
- Runtime authority: SCRIMED Work durable AAL2 control plane
- Orchestration: planner-specialists-verifier-human-gate
- Mutation authority: AAL2 + tenant RBAC/RLS + durable store + idempotency + approval

## Registries
- Agents: 14
- Skills: 20
- Workflows: 9
- Semantic definitions: 20
- Provider policy profiles: 6

## Governance
- Verification eligible for completion: false
- Trust score: 85
- Objective drift detected: false
- ConsequenceBench status: awaiting-evaluation-results
- Cross-platform release blockers: 4

## Safety Boundary
SCRIMED Intelligence Control Plane unifies governed agents, skills, workflows, context, routing, verification, benchmarking, artifacts, capital intelligence, voice simulation, compute resilience, learning proposals, outcomes, and audit metadata. It accepts synthetic or de-identified fixtures only and does not authorize autonomous clinical care, PHI processing, EHR writeback, payer submission, investor outreach, securities representations, production deployment, certification claims, or customer activation.

## Next Production-Hardening Step
Remove or substantiate the public testimonial, bind the current build to a clean reviewed source revision, then apply pending durable-store migrations to an approved nonproduction Supabase target for strict AAL2 smoke.