Directing is rejecting

The model will give you something that compiles, renders, and looks finished. That is not the hard part anymore.

Directing is what you do next. You reject the plausible thing until the true one is left.

People talk about directing as if it were prompting: a better brief, more iterations, a longer system prompt. That is logistics. Prompting is how you start a run. Directing is how you decide the run is over. And which of the things it produced is allowed to stay.

Generation used to be the scarce part. You paid for it with hours, with a file, with a person. Now a finished-looking interface is cheap. The expensive part moved. It is the decision to keep something. Every extra variant, every invented prop, every motion that exists to prove the tool works, stays in the product. The rejected ones only cost the afternoon.

That is why the job did not become "write better prompts." It became easier to see who is actually designing. The model will keep offering the impressive take. Someone has to still be there after the generation finishes and say no.

In one of my projects, I needed a badge to show status (success, warning, error), the small label that has to hold next to a title, or on a table cell. We already had the quiet one: a soft tint, dark type on a wash of color. The model proposed a solid-fill: the loud pill, light type on a color field. It looked like a product. It failed contrast, and we did not need a second family of badges. I rejected it.

That is the whole shape of the work. Not a tour of projects. One no, defended.

A model cannot do that for you. It has no cost for being wrong in a way that still looks right. It will not sit with the thing in six months. It will not hear a teammate ask why the other version is gone. You will.