Open-source tooling and field-tested patterns from shipping governed agentic systems in production.
Build, open-source tools and Claude Code skills, cloneable and runnable from a fresh checkout.
Selected essays point to the doctrine behind the build; the full archive lives at /thoughts.
Available for staff/principal AI-systems roles and speaking.
Running agents in production? I do a five-day readout on your own logs: cost per verified success, and what a quality floor would have caught.
The Authority Gate, Made Runnable: Fail-Closed Merge Admission for Agent-Written Code Pre-Execution Authority Gates: Why Governance Must Be Evaluated Before State Mutation The Four-Layer Enforcement Stack The Merge Is a State Mutation Why Enterprise AI Fails at Runtime, Not Capability Full archive Live signal log GitHub