> if I am not even quite sure what exactly I want to build myself

Sounded to me like you need a plan.

My approach is to take the statement of work or problem definition and iterate on that myself until I'm really clear on what is the goal. I therefore have a good some good ideas about what the plan should be.

If extending an existing application, which is usually the case, then make use of the plan documents that I had written before AI arrived on the scene. These sre documents in markdown form that say step-by-step how to, for example, add a new report to the system.

You tell it, "let's brainstorm, don't implement anything yet". Then you talk about what you want to build and hammer out all the corner cases. Then you tell it "now do that".

> How does it otherwise work if I am not even quite sure what exactly I want to build myself?

It makes some plausible choices and you can retroactively ask it to make different ones later, if you want.