← Selected work

AI agent reliability · AI security

Agent Review Control

The public Contract + Evidence + Verdict architecture for controlling and reviewing AI coding-agent work.

StatusPublic architecture and dogfood evidence; active deterministic implementation remains private.
ContractFrozen before work
EvidenceBound to exact change
VerificationIndependent and fail-closed
DecisionHuman-controlled

01 / Problem

Why this system exists

Coding agents can execute successfully while drifting from the approved assignment or presenting evidence that does not belong to the exact change under review.

02 / Architecture

How state moves

  1. 01Frozen contract
  2. 02Execution controls
  3. 03Bound evidence
  4. 04Independent verification
  5. 05Trust Brief
  6. 06Human approval

03 / Decisions

Engineering choices

  • Freeze approved intent and boundaries before implementation begins.
  • Treat agent claims as untrusted until supported by attributable evidence.
  • Keep verification independent from the agent that produced the work.
  • Track evidence through pending, current, stale, and refreshed lifecycle states.

04 / Boundaries

What this does not claim

  • ARC does not prove code correctness, safety, or semantic truth.
  • Private doctrine, customer evidence, operational controls, and source remain private.
  • CI, security tools, human review, and ARC evaluate different properties.

See the code and documentation.

View repository ↗