I've built a few things recently, small projects almost entirely through conversations with AI. A lemon-themed scrapbook for Valentine's Day, a website where you can leave anonymous sugarcubes for people, and this very portfolio site. No design tools, no real hands-on coding on my part. I just described what I wanted and kept iterating until it felt right, and the results were genuinely good. Not "good for a vibe-coded project" good, but actually, properly good. That made me think about what I was actually contributing to the process.
What I realized I was doing
I wasn't building. The AI was building. What I was doing was more like directing. I'd say things like "this feels too corporate" or "I want it to feel more like a physical object" and the AI would adjust. I was reacting, refining, pointing at things and saying "more like this, less like that."
I noticed that the quality of what came out depended almost entirely on how specific I could be. When I said "make it look nice" I got something generic. When I said "I want this to feel like a well-designed instrument panel, tactile, deliberate, every element earning its place" I got something with actual personality. The AI didn't care either way, it just executed on whatever I gave it. The specificity was entirely on me.
Where this comes from for me
Here's the thing, I've never been a creative person, not in the traditional sense. I can't draw, I don't have a design background, I never opened Figma for fun. But I've always been weirdly particular about things looking right. I'd spend way too long adjusting spacing on a slide deck, get genuinely bothered by a font choice that nobody else even noticed. I admired beauty and good design even when I couldn't produce it myself. I had classic nerd energy, appreciating the craft without having the craft.
What made this click for me was a data visualization course I took in January 2025, in grad school with Dr. Chris Bryan. It was honestly one of the best classes I've ever taken. He taught us about affordances, how design communicates what something does just through how it looks, why some charts work and others lie, what makes a visualization not just accurate but actually good. I learned D3.js and put in way more effort than I needed to, not just because the assignments required it, but because I wanted the output to be beautiful. I'd be tweaking color scales and transitions and axis labels long after the functional requirements were met. That class gave me a vocabulary for something I'd always felt but couldn't articulate.
I think that's what people mean when they talk about taste. It's not some innate gift. It's the accumulation of everything you've ever noticed and cared about, and now there's finally a way to use all of it directly.
Something I hadn't thought about before
I always assumed the hard part of making things was the making. The coding, the designing, the technical knowledge. And for a long time, it was. But having these conversations with AI, I realized the hard part had quietly shifted to something else entirely: knowing what you want and being able to say it clearly.
Which sounds simple, but it's really not. Saying "make the buttons feel like physical hardware" requires you to have seen enough physical hardware to know what that even means as a design language. Saying "I want mid-century modern principles but warmer" means you need to know what mid-century modern looks like and what "warmer" means in that context. All of that comes from just... having paid attention to things over the years. Noticing details. Caring about stuff that didn't seem useful at the time.
The part that's a little uncomfortable
I used to think taste was a nice-to-have, that the real value was in execution, in whether you can actually build the thing. And I still respect that deeply. But I'm starting to see that when AI handles the execution, taste becomes the differentiator. Two people with the same AI will get wildly different results based purely on what they bring to the conversation.
That's exciting, but it's also kind of humbling. Because "I don't know how to code" was a concrete problem with a concrete solution, go learn. But "I don't have enough references" or "I haven't paid enough attention to good work" is a much more personal gap to sit with. There's no bootcamp for taste. It's just years of looking at things and giving a damn.
What I've been doing differently
Mostly just paying more attention. To interfaces I use every day, to physical products, to spaces I walk through. Not studying them exactly, just noticing what works and trying to figure out why, building up a library of references I can pull from when I'm describing something to an AI.
And being more specific when I describe things. Instead of "make it minimal," I try to say what kind of minimal. Instead of "make it fun," I try to reference something specific that captures the kind of fun I mean. The AI responds to precision, and I've been trying to get better at providing it.
I think the future quietly belongs to the people who have strong opinions about details nobody else cares about. The kind of person who'll spend twenty minutes deciding if a border radius should be 8px or 12px, who'll agonize over whether a hover state needs 150ms or 200ms to feel responsive without feeling jumpy. That used to just be obsessive. Now it's the entire skill.
I don't think I'm particularly good at this yet. But I'm getting better, and the gap between what I can imagine and what I can actually bring into existence is smaller than it's ever been. That feels like something worth paying attention to.