Topics

Four recurring themes run through the series. Each is a lens on the same shift — from treating AI as a clever tool to engineering the systems that make it reliable.

• Vibe coding vs. reliable systems

  The paradigm shift at the heart of the series: from typing into a chat window and hoping, to engineering the systems that make AI reliable.

  5 essays

• The harness

  The engineering substrate around a coding agent — specifications, validation, workflow, context — that turns probabilistic output into production-grade software.

  15 essays

• Specify. Direct. Validate.

  The loop that replaces reactive prompting. Write the spec, direct the agent against it, validate the output — then fix the spec, not the code.

  5 essays

• Architect-CEO

  How leadership roles change when agents execute. Engineers define outcomes and validate them; the organization writes software differently.

  6 essays

• Coherence

  Why piecemeal AI produces silos and lock-in, and why AI and your existing systems have to be raised together.

  2 essays

• Foundation

  Why enterprise AI failures are architectural, not intelligence failures — and how to start fixing the foundation one load-bearing corner at a time.

  1 essay