The way I work has drastically changed in the last 3 months.

AI is everywhere in my process now, spearheaded by Claude.

And honestly… I might stop using Figma in the very near future.

In this issue I’ll be sharing how my design process got impacted by AI (in a good way), how you can get better design results with tools like Claude, and what needs to happen for me to ditch Figma once and for all.

How & where Claude took over my design process

I never had the feeling AI will ever replace me.

I still don’t think it will.

However, AI will dramatically improve my work.
It already did in 3 areas of my design process (the 3rd one had the biggest impact):

1. Labels, and UX copy

It started simple. I didn’t know if I should name a button “Discard” or “Cancel” for a specific action.

So I shared the problem and the context with Claude, and it immediately spit out 3 reasons why “Discard” was the better choice there.

Since then, I started asking Claude about Modal Headlines, Chart Titles and even Tooltip texts.

Sounds like details, but I used to spend hours on those texts, just to make them perfect.

Now, those hours turned into minutes.

I also got better at prompting. You have to structure those prompts properly.
Is this something you would be interested in? My Prompt Structure? If yes, respond and let me know, I will send you my current structure (not perfect yet, but works like a charm for 99% of my tasks).

2. Design Presentations and UX Psychology

When designing a new concept, I like to create presentations in Figma Slides, and back up my design decisions with:

• Internal customer data
• UX Principles (like Cognitive Overload)
• And metrics from scientific papers

This research usually took hours.

I just wanted to be confident in case someone asked “why does the delete button need to be red”?

Now, Claude does it all.
It still sucks when it comes to finding good sources for user metrics, however it’s amazing with finding the right UX principle I unknowingly applied.

Again, hours turned into minutes.

3. No more prototyping in Figma

I used to create hundreds of screens in Figma, and then connect them up in a prototype and present it.

The process was:

1. Design in Figma
2. Record a Loom and present the design
3. Get feedback in Loom or the Figma file

For the last 5 projects, I did some explorations in Figma, but immediately went to Lovable to build a prototype out of it. And my god, it works so well.

Now my process looks like this:

1. Design a bit in Figma, just general ideas
2. Prototype in Lovable
3. Send the Link and ask for feedback in Slack

And people love the prototype!

It uncovers feedback that people did not think about with the Loom.​
Because they get to play around.
Find issues.
And maybe use the prototype 2 or 3 times until they come back and add more feedback.

The time saved is minimal, maybe it takes even longer to prompt sometimes, but the impact it has for my customers and the feedback I get: Huge!

Where Figma still shines

Prototyping already sucked in Figma. So doing this better is an obvious first step.

However, when it comes to:

• Using FigJam for Userflows and Design Interviews
• Using Figma Community to quickly find graphics and UI components
• Using UI Kits to jumpstart ideation
• And of course, design systems, documentation and keeping track of ideas

Then, Figma is not “ditchable” yet.

At least for me.

I know, there are better tools, and with MCPs I can get Claude to do stuff for me, but these things take time and effort.

So, will I ditch Figma?

No, not for now.

Even if all the tasks I need Figma for get replaced, there is still the huge benefit of collaboration between not only designers and devs, but also researchers, marketers and PMs, who all built huge knowledge bases in Figma.

Did you integrate AI in your design process?

If yes, how? I would love to know! Just respond to this email! I try to answer every response :)

​