How do you teach an AI your taste?

You can write down a design system. You can write down your process. You cannot write down your taste, which is annoying, because taste is most of what makes a designer a designer.

Taste is the thing that goes "no, not like that" without always being able to say why in the moment. It's the reason two designers with the same brief and the same components hand back different work. So when I started leaning on an AI for real design work, this was the part I was sure it would never get. And mostly it didn't. It would do something slightly off, I'd correct it, and next week it would do the exact same slightly-off thing again, cheerfully, like we'd never met.

The correction that evaporates

That's the real problem. Not that the AI has bad taste. It's that your corrections evaporate. You fix the same thing forever because nothing you say sticks past the session.

So I built a feedback loop. Two ways in. One is passive, it just watches what I accept and what I throw out and quietly notes the pattern. The other is me saying it out loud, "no, we always do it this way," when I catch something.

Each of those becomes an entry in a profile. Not a global rule for everyone, a profile per designer, because my taste and my teammate's taste genuinely differ and pretending otherwise flattens both.

The part I almost got wrong

Here's the trap I walked into. The first version turned every offhand comment into a hard rule instantly. I muttered one thing about spacing on a bad day and the AI treated it as law forever after. That's worse than no memory, because now it's confidently wrong in my name.

So a preference doesn't become a rule the first time I say it. It starts as a candidate. Only when the same thing shows up again, when it's clearly a pattern and not a mood, does it get promoted to something the AI actually follows. Say it once, it's noted. Say it twice, it counts.

That one guard is the difference between an AI that learns your taste and one that over-fits to your worst Tuesday.

Taste can't be specified up front, but it can be accumulated. The move is to capture preferences as rules you can promote, not corrections you repeat, and to make the AI earn a rule before it trusts it. Do that and the thing slowly stops doing the slightly-off version. Which is about as close to "it learned my taste" as I need it to get.

---

Part of a series on building an AI collaborator for our design team at Xflow. Each post stands on its own.