Xavier Bertels

The general design vector in AI powered apps is either chat, or voice. That seems like bad news for designers. But I think it opens up an opportunity.

Imagine you’re on a busy bus. You’re in a waiting room. Your spouse is sleeping. Voice works in some scenarios, but it sure doesn’t work all the time. It doesn’t jive with how a lot of humans live and work.

Then, there is chat. If you think about it: text is the ultimate design system. We’ve come up with a system that allows us to convey a lot of—but not all—meaning by combining a very limited set of little drawings. And language models are incredibly good at generating interfaces on the fly that allow users to “do stuff” by sending these little drawings back and forth.

But text is also an incredibly cumbersome way to interact with computers. When was the last time you typed something on Instagram? It’s a billion dollar business model built around swipe, tap, swipe, double tap.

Text is a stopgap. Eventually, we’ll want shorthands again. We’ll want something visual. Perhaps even something tactile. The interface may be generated on the fly though. And this is where designers will shine once again. We’ll need people to think about new systems, new shorthand, new ways of communicating visually.

It’s a very exciting time to be a designer.

A friend once told me that many people seem to be exhibitionist masochistic thrill seekers. Daily ice baths, climbing Mount Everest, ultramarathons. It seems like there’s no end to the list of extreme things we put ourselves through.

But there is a subtle difference between masochism and working through adversity. It’s how you come out on the other side of it. There’s no growth to be found in masochism. It’s an act. Combined with an exhibitionist streak it might lead to Instagram likes or a short lived dopamine fuelled ego boost. The effect wanes and we soon need another hit. It’s a loser’s game.

But that should not be an excuse to avoid doing something difficult. Perhaps something that seems like it’s doomed to fail. It can lead to some of the most lasting growth. Our most remarkable achievements lie on the other side of very difficult things.

I’ve been playing around with Windsurf, but it hadn’t really clicked until today.

It was kind of daunting. First I had to understand the UI. Then I had to find a good size project. Fortunately, I’ve been playing with an idea at work that the developers simply don’t have the time for.

Then, four hours of vibe coding later, I suddenly had a working prototype. Of an API product. Something that’s basically only a backend application. Including API specification and deployment to Hetzner Cloud. Written in a language I don’t understand. For the record: I can’t code a backend application like this on my own.

But now, I can? Cool. And wow. This is impressive.

The best tools create a state of flow and that’s exactly what it does. No need to read long blog posts and extract what’s relevant for my use case. On top of that I’m learning more about coding than ever. So not only can I build fully working apps, I can also learn about coding in an immersive environment that encourages exploration and making mistakes that lead to more learning moments.

What a wonderful time for kids who will have access to this tech when they’re young now. What a great way to learn coding.

When new tools become available for us to play with, we can get caught up in our enthusiasm. Creativity starts to flow. Ideas pop up. The environment feels energetic and we start to sketch, design, execute.

This is an important part of building products. An equally important part is to scrutinise and edit our outcomes in the second phase. Perhaps a solution looks good on the surface but it doesn’t really solve a problem and it’s therefore ugly. Or maybe we don’t really need to make millions of energy consuming API calls to OpenAI when the same problem can be solved elegantly by filling a blank in a template text.

This is the difference between building, and building with care.

It’s been a while since I wrote anything here. Perhaps it’s because I’ve been busy? More likely it’s because I haven’t made the time to write. Or maybe I just didn’t feel like I had anything to say?

Anyway, just writing this, I feel better already. I’ve been meaning to write more. I have no idea if anyone still reads blogs in 2025. Maybe it’s just LLM scrapers. Whatever the case may be, I still want to write, because I enjoy it. And because I want to continue to be good at writing. I want to hone this skill and get better at it. I want to be better than the en-dashed uninspired AI goop we find in our digital surroundings every day.

I’ve always admired Seth Godin, who has been writing every single day, non stop, for over a decade. I’m sure he’s become a sharper thinker because of it. So maybe I want to write because I want to think more. I enjoy thinking a lot. Even if there isn’t always a conclusion.

Voilà.