TJ Larkin

AI workflows

How can a non-technical founder build software with AI?

Short answer

Talk to the coding agent in plain English, one chat per codebase at a time, and ignore its time estimates. I'm not a developer. Almost everything that got my form product ready to launch went through Codex by voice or text, not by me editing code.

I've shipped real products this way: subscriber forms, media kit builders, dashboards, client onboarding. Here's what actually works.

How fast it really is

  • The admin backend for a survey and quiz tool: about 15 minutes, built against an existing design system.
  • A media kit builder: four or five AI coding sessions over a couple of hours.
  • A dashboard pulling Meta ads data from nine ad accounts plus newsletter stats: Codex did it in one attempt after Claude Code failed at the same task.
  • A post-sales-call automation that reads the call transcript, builds a proposal site, makes a payment link, and sends onboarding once paid: under 48 hours.

My team builds features about five times faster and cheaper than before.

What bites non-technical founders

  1. Parallel chats on one codebase. Sometimes they screw each other up. One at a time.
  2. "Fixed" doesn't mean live. The tool fixes things locally and doesn't say whether they're live. Ask.
  3. Made-up problems. AI tools report bugs that don't exist. I've spent about 40 hours over four months tuning my agent instruction files and skills to cut that down. Worth every hour.
  4. The last 10%. AI gets you 90% in an hour. Multi-step workflows are where the last 10% gets hard.

Scale yourself

When I bring on an operator, I clone my whole setup onto their machine: instruction files, brand guidelines, project context. They become an extension of me with fewer permissions.

Answered by TJ Larkin. From team and partner calls in May and June 2026. Last updated .

Related answers

TJ Larkin / Answers / AI workflows