George Drag

Case study · AI build system · 2026

Boop

A harness for getting the most out of AI and human work together.

How it works

  1. The spark: a human idea.
  2. Spec: the CTO agent, Fable.
  3. Spec review: another agent checks it against the real code.
  4. Build: Codex writes every line.
  5. Self-check: ruff, mypy --strict, pytest.
  6. Gate: full suite on a real database, zero skips.
  7. Review: another model tries to break it.
  8. Fails? Back to Codex, three rounds, then me.
  9. Merge: a second account approves.
  10. Shipped: and written down.

The crew is one part of a bigger system I run at home, with a brain for me, a brain for every project, and one assistant I talk to for all of it.

Faster, smarter and cheaper every day.

Every model is plug and play.

  1. Fable 5.1 writes the specs.
  2. GPT-5.6 Sol builds with Codex.
  3. Opus 5.5 runs the crew.
  4. GPT-6 Astra gives a second opinion, and the next model plugs right in.

Roadmap

shipped

  • A full security stress test.

    The crew tried to break itself on purpose and fixed everything it found.

  • A live dashboard.

    One place to see what every agent is working on.

next

  • Ship a product start to finish on its own.

    Designed, built, reviewed and shipped by the crew.

later

  • A daily self-check.

    An automatic audit that hunts for weak spots before they cause a problem.

  • One coordinator across every project.

    A single role keeping all the work in sync.

  • Shared memory across projects.

    Lessons from one build carried into the next.