StrongDM built a system where humans never write code and never review code. The entire engineering workflow is delegated to AI agents. Ethan Mollick covers this in One Useful Thing:

A three-person team at StrongDM, a security software company focusing on access control, announced they had built a Software Factory — a way of working with AI agents that relied entirely on the AI to write, test, and ship production software without human involvement. The process included two (quite radical) rules: “Code must not be written by humans” and “Code must not be reviewed by humans.” To power the factory, each human engineer is expected to spend amounts equivalent to their salary on AI tokens, at least $1,000 a day.

$1,000 a day per engineer. The humans write the roadmap; coding agents build the software while testing agents spin up simulated customer environments and stress-test it. The agents loop until the results pass, then humans review the finished product, never the underlying code. Simon Willison and Dan Shapiro both observed the Factory in operation and wrote detailed accounts.

Mollick’s larger argument is that experiments like this matter beyond their specifics:

We can see the shape of the Thing now, but we can still influence the Thing itself, and what it means for all of us. We clearly don’t have rules or role models for how AI gets used at work, in schools, or in government. That’s a problem, but it also means that every organization figuring out a good way to use AI right now is setting a precedent for everyone else. The window to shape the Thing may not last long, but it is here now.

Design doesn’t have its rulebook for this yet either. Our time to define it is now.