I've been using codex to design and build a product that is a fairly conventional looking app - think of a gmail like experience - with some delicate synchronization across devices.

I find that I need to invest a whole lot in high level design myself to get Codex to create a suitable architecture and make the right tradeoffs. It's more like I am designing and Codex is reviewing and occasionally we brainstorm. When I tried having it design based on requirements, it went wild with an unsustainable design / architecture.

And I use things like plan mode etc. My experience is unlike what I read in most vibe coding exploits.

I wonder if I am doing something wrong. Is there a good canonical example of a project built with Codex or even Claude Code that shows how the human and AI interact that I could use as a reference

> occasionally we brainstorm.

Seriously, how do you brainstorm with an entity that would 180 if pushed a bit..How can you take anything it say at face value?

I've been on a similar path, and I used to put time in high level design, as it was basically required in some cases. But not a lot of time, because smaller agents research, perform small tests, whatever to inform the high level design. Working incrementally seems to help, maybe prompting a bit more often, but the same can be accomplished with well defined checkpoints.

Then generalize + standardize that process, get an agent to replace you as high level designer so you can manage a team of high level designers, etc etc