Writing

Notes from building an AI software engineering harness — what makes agent-written code reliable, where it quietly breaks, and what twenty years of shipping software says about the current moment.

  • Harness Engineering: Why I Stopped Blaming the Model

    The model is not your bottleneck. After building two production apps with zero human-written code, I'm convinced the harness — the constraints, verification loops, and enforcement around the model — is the whole game.

    harness engineeringai codingagentic codingverification
    Read it
Back home RSS