AI Won't Replace Designers. But Designers Who Use It Will Work Differently.

 

I used to think coding wasn't part of my job as a designer.

My job was to understand users, design flows, create interfaces, prototype them, and hand everything over to developers.

Then AI changed the workflow.

Not by turning me into a developer.

But by making the distance between idea → prototype → product much smaller.

That's where AI workflows and vibe coding became interesting to me.

I'm not trying to become a developer

When I say I use vibe coding, I don't mean that I've suddenly become a software engineer.

I still think like a designer.

I start with:

What problem are we solving?

Then:

What should the experience be?

Then:

How should the interface behave?

The code comes after that.

Tools like AI coding assistants, v0, and other generative tools allow me to turn those decisions into something interactive much faster.

Instead of spending hours imagining how an interaction might work, I can sometimes build a rough version and experience it myself.

That's a completely different feedback loop.

From static design to working prototype

Traditional workflow:

Idea → Figma → Prototype → Developer → Implementation → Feedback

My AI-assisted workflow can look more like:

Idea → Figma → AI → Working prototype → Test → Iterate

The important difference isn't speed.

It's feedback.

A static prototype can tell me whether a flow makes sense.

A working prototype can reveal things I didn't notice in Figma.

Maybe an interaction takes too many steps.

Maybe the loading state feels strange.

Maybe the hierarchy doesn't work once real content appears.

Maybe the empty state completely changes the experience.

These are things I can discover by actually using the product.

AI is another design material

I've started thinking about AI the same way I think about components.

It's a tool inside the workflow.

I can use it to:

Explore

Generate different approaches to a problem.

Challenge

Ask AI to identify edge cases or assumptions I may have missed.

Prototype

Turn a design direction into an interactive interface.

Write

Generate first drafts for UX copy, documentation, or product content.

Analyze

Structure research findings and identify patterns that I can investigate further.

Iterate

Try multiple versions without treating the first solution as precious.

But there's an important rule:

AI can accelerate my thinking. It shouldn't replace my thinking.

The dangerous part of AI

AI makes it incredibly easy to create something that looks finished.

That's also the trap.

You can generate a beautiful dashboard in minutes.

It can have:

  • Perfect cards

  • Nice gradients

  • Beautiful charts

  • Smooth animations

  • Responsive layouts

And still solve absolutely nothing.

That's why I try to separate:

Generating an interface

from

Designing a product.

The first can be automated surprisingly well.

The second still requires judgment.

My AI workflow

My current workflow is roughly:

01 — Think

I define the problem, user, context and desired outcome.

No prompting yet.

02 — Design

I explore the experience in Figma.

User flows.

Information architecture.

Wireframes.

Components.

High-fidelity UI.

03 — Prompt

Once the design direction is clear, I describe the interface and behaviour to an AI coding tool.

I don't just say:

“Build this dashboard.”

I provide context.

What the user is trying to accomplish.

What information matters.

How components behave.

What happens in different states.

What shouldn't happen.

04 — Vibe code

I use AI to turn the design into a working prototype.

Then I interact with it.

Break it.

Try weird inputs.

Resize it.

Test empty states.

Test long content.

Test errors.

05 — Critique

This is where the designer comes back into the loop.

I ask:

Does this actually solve the problem?

Not:

Does this look cool?

06 — Iterate

I change the design.

Change the prompt.

Change the implementation.

Test again.

The loop becomes:

Design → Build → Experience → Critique → Improve

The designer's role is changing

I think one of the biggest opportunities for designers isn't learning to write thousands of lines of code.

It's becoming comfortable enough with technology to communicate with it.

Understanding:

  • HTML

  • CSS

  • Components

  • APIs

  • Data structures

  • Responsive behaviour

  • States

  • Logic

  • Constraints

gives designers a much better understanding of what they're actually designing.

You don't need to become the engineer.

But knowing how the product is built makes you a better product designer.

Vibe coding changed how I think about feasibility

Before experimenting with AI coding tools, I would sometimes design an interaction without knowing how difficult it would be to implement.

Now I can test the idea myself.

Sometimes I discover:

“This is much easier than I thought.”

Other times:

“This interaction isn't worth the complexity.”

Both outcomes are useful.

The goal isn't to make everything possible.

It's to make better decisions about what should exist.

The future I want to work toward

I don't want to be a designer who says:

“Here are the Figma files. The developer will figure out the rest.”

I want to understand enough of the entire product loop to participate in the conversation.

Research → Product thinking → UX → UI → AI → Prototype → Code → Testing

Not because designers should do everyone's job.

But because the boundaries between disciplines are becoming more fluid.

AI makes that even more obvious.

My rule for using AI

I have one simple rule:

Use AI to remove friction, not responsibility.

Let it generate.

Let it explore.

Let it code.

Let it challenge assumptions.

But keep the important decisions human.

Because the value of a designer isn't how quickly they can produce a screen.

It's knowing which problem is worth solving, why it matters, and whether the solution actually helps someone.

AI can help me get there faster.

It doesn't decide where I should go.

Comments

Post a Comment

Popular posts from this blog

What Running My Own E-Commerce Brand Taught Me About Product Design

  What Running My Own E-Commerce Brand Taught Me About Product Design I didn't learn product design only from courses. I learned a lot of it by breaking things in a real business. Before I started seriously pursuing product design, I was running an e-commerce jewellery brand. I was responsible for almost everything: Product photography. Catalogues. Packaging. Marketing. Customer conversations. Orders. Payments. Operations. At the time, I didn't think of these things as “UX problems.” I just thought: This business is becoming difficult to manage. Looking back, I realize I was experiencing product design problems every day. The first lesson: messy workflows create invisible costs Customers could reach us through different channels. Some orders came through marketplaces. Some came through Instagram. Some came through WhatsApp. Information was distributed across different places. That created small problems. A customer would ask about an order. I'd search through conversations....
Read more

Empathy Is Not Guessing What Users Feel

  Empathy Is Not Guessing What Users Feel I used to think empathy meant understanding how the user feels. Now I think it means something slightly different: Being willing to accept that I might be wrong about them. That's a much harder thing to practice. As designers, it's easy to look at a problem and immediately create a solution. A user can't find something. → Add a button. Users are confused. → Improve the copy. People aren't completing a flow. → Reduce the number of steps. Sometimes those solutions are right. But before designing them, there is a more important question: Why is this happening? Empathy starts with curiosity When I started learning UX, I often approached problems with assumptions. I thought I knew what users wanted because the solution seemed obvious to me. But users don't experience products the way designers do. They don't see our information architecture. They don't know our design system. They don't understand the reasoning behind...
Read more