How I Build

Every line of code here (a couple dozen web applications, an iOS suite, and a private fleet of infrastructure) was written by AI coding agents. The interesting part is not that AI wrote the code. It's the division of labor that emerged after the naive version, one capable model doing everything, kept failing in specific, logged ways. Nearly every role below exists because something went wrong without it.

The team

The work is done by a small standing team: AI agents I hand tasks to, each a distinct model with a pinned skill tier and a call sign, plus the functions that hold it all together (compliance, change control, audit, and the rest), and a founder who judges outcomes in plain English. Everyone reports through one verification gate. The dogs run Corporate Security.

Why this shape works

• Verification is the load-bearing wall. Every bulk run has caught executor errors; the citation-less claims were the false ones. Delegation without verification is just hoping, at scale.
• Tiering is an economics decision with a quality ceiling. The expensive model spends its attention on judgment (scoping, verifying, applying), not on search loops.
• Independence is what testers are for. The model that wrote the code is the worst-positioned to find its blind spots. A different model, a different vantage point, a different account: each removes a class of shared assumption.
• Structure beats capability. The failures that shaped this org were not model-intelligence failures. They were missing roles: no verifier, no independent tester, no auditor, no gate.
• Every role earns its box by a logged failure. If a role can't point to the failure it prevents, it's ceremony.