Zero to App with AI, Part 5: Scaling Me, Not the AI

Around the middle of the project something flipped: the agent was no longer the bottleneck. I was. One session built a feature faster than I could specify the next one. Part 2 warned that multiplying agents multiplies cost. This part is about the places where parallelism and delegation genuinely paid, and the structures that kept it from becoming chaos. Parallel phases in worktrees The roadmap had independent phases queued up. Daily check-ins and a settings/themes page touched almost disjoint code. So they ran as separate sessions, simultaneously, each in its own git worktree, launched from pre-written, self-contained prompts. ...

July 17, 2026 · 5 min · 984 words · Nate

Zero to App with AI, Part 3: The Phase Rhythm

Part 1 and Part 2 covered the setup: docs as memory, cost controls in config. This is the part where the app actually got built, a core logging loop, a plans system, and a PR detection engine, and where the working rhythm emerged that carried the whole project: One phase per session. Review at every phase boundary. The human tests between phases. That is the entire method. The rest of this post is what it looks like in practice and what it caught. ...

July 13, 2026 · 6 min · 1126 words · Nate

Zero to App with AI, Part 2: Keeping It Cheap

The dirty secret of AI-assisted development is that the naive way to do it, one enormous chat session, the biggest model, all day, is expensive out of proportion to what you get. Before writing much code for RepRepo, I set up cost controls. The interesting part is that almost none of them rely on me remembering to do anything, which turns out to be the whole trick. If you missed it, Part 1 covered the docs-as-memory setup this all builds on. ...

July 11, 2026 · 6 min · 1096 words · Nate

Zero to App with AI, Part 1: Write the Docs Before the Code

This is a different kind of post for this blog. Less BGP, more JavaScript. I built and shipped a real app, RepRepo, a workout tracker, essentially over one weekend, working with an AI coding agent (Claude Code, in my case, though most of this translates to any of them). Not a todo list demo either. It has a plans system, PR detection with unit tests, multi-user auth, security hardening, nightly backups, and tagged releases deployed by CI, and it is running on the public internet where I actually use it at the gym. ...

July 9, 2026 · 6 min · 1261 words · Nate