Guarding the correctness of a service I build alone with AI through structure, not attention

Summary

Having AI agents split into roles write much of the code, I have spent about two weeks building a paid membership service on my own. Once you have AI write code, a problem shows up right away: who checks whether the code the AI wrote is correct, and how. Since I build alone, I cannot afford to place, apart from whoever writes the code, someone whose role is to doubt it and investigate.

So I stopped relying on the author reviewing the code carefully to keep it correct. Instead, I reshaped things into forms where mistakes are less likely, and, apart from the AI that carries development forward, I set up an audit independently whose only aim is to look for how it breaks, and had it verify. This way, I have caught four defects before publishing. Every one was a defect that broke only when parts were combined or a state changed, even though every per-part test passed. In this article I write how far I delegate to AI, how I get the rules to an AI that starts fresh each time, how I have an independent audit find the mistakes the author cannot find, and how I finally reshaped things into forms where mistakes are impossible.

Who this is for and what you can take away

I write this for someone who, alone or in a small team, is trying to build a paid membership service while having AI write the code. By the end, you can take away a way of thinking: where AI may proceed on its own judgment, and from where a person checks first and then instructs, drawing that line not by the kind of operation but by the conditions that must be met. It is based on the record of building this site alone with AI.