Building a full product with one founder and a team of AI agents
I am building Rewire, a trading-psychology drill app, and the build is one person plus a set of AI agents with defined roles: a frontend one, a backend one, a QA one that walks the whole user journey, a perf one, and a few for marketing research and drafting.
What I spend my time on: writing the trading logic, designing the scenarios, and making the judgement calls about what a disciplined trader actually does in a given spot. The agents turn that into working code, tests, and a changelog, usually by the afternoon. I review every scenario and every deploy.
What changed for me: a build day used to end with a plan for tomorrow. Now it ends with something shipped. The tradeoff is that the agents are literal, so the specs have to be tight or you get exactly the wrong thing built well.
Two things I am still working out:
Keeping a consistent visual and voice identity when different agents touch the UI. I ended up writing a hard rules file they all load.
Where the human review has to sit. Code review I can be light on. Anything that touches money, auth, or the actual trading content I read line by line.
If you are building this way, where did you land on the review line, and how do you stop the agents from quietly drifting the design?
Replies