Why Figma might be the last tool we'll love
We’re not witnessing the death of design. We’re witnessing the death of design-ing.
I remember the exact meeting where everything changed.
It was 2018 at Grab. We were a design team of over a hundred people, all using Sketch, all dropping files into Google Drive, all pretending that was collaboration. It wasn’t. Version conflicts and naming chaos: homepage_final_v3_FINAL_USE-THIS-ONE.sketch. You know the drill.
We tried Abstract. We tried Zeplin. Band-aids on a broken workflow.
Then someone pulled up Figma in our weekly sync. Two cursors on the same canvas. Real time.
We were sold in under five minutes.
Migration took three months. A hundred-plus designers exporting out of Sketch, rebuilding libraries, relearning muscle memory. Painful. But nobody asked why. Collaboration wasn’t a feature of Figma. It was the product.
Fast forward to today, and I’m getting déjà vu.
The canvas is moving again
A new wave of tools is here, and they don’t treat pixels as the canvas anymore.
Google Stitch, Paper and Pencil evolved into an AI-native infinite canvas paired with a design agent that reasons across your entire project. You don’t open a blank file. You describe what you want, drop in a screenshot or a few lines of code, and Stitch generates working UI. They’re calling it “vibe designing.” You can literally talk to it. “This header feels too heavy.” It adjusts.
Then last week, Anthropic launched Claude Design. Different bet, same destination. You point Claude at your codebase, and it builds a design system from what already exists. Your colors, typography, components. All reverse-engineered from your live product. Every prototype after that is automatically on-brand. When you’re ready, it bundles the whole thing for Claude Code, the same AI that writes the production code.
Three days before that launch, Anthropic’s CPO Mike Krieger resigned from Figma’s board.
Make of that what you will.
Figma assumed you start with a blank canvas and place elements on it. These tools assume you start with intent and refine the output.
That’s a category shift.
Design used to happen on the canvas. Now it happens in the conversation.
I write weekly playbooks for designers using AI. If that’s you, subscribe to Design AI Stack.
The wallet screen test
A few weeks ago I posted two screenshots in our design team’s group chat at Botim. One was our Wallet screen, hand-designed by a product designer. The other was the same screen, generated end-to-end by Claude.
That moment told me everything I needed to know. AI tools like Claude Code, Cursor, Claude Design, and Stitch are already remarkably good at production-ready UI. Give them a prompt, a design system, and some context, and they ship something competent, consistent, and on-brand.
Not inspired. But shippable.
And for the vast majority of screens in the vast majority of products, shippable is exactly what you need.
What AI still can’t do
This is where designers push back. “AI can do my job?”
That’s not what’s happening. What’s happening is more interesting.
There are two types of design work: the creative and the mechanical.
The creative is the thinking. Understanding a user’s pain. Reframing a problem. Deciding what not to build.
The mechanical is the execution. Mockups, variations, specs, assets, consistency.
The mechanical part? Give it to the machines. Fully. Without guilt.
The creative part is still ours. And it matters more than ever.
Here’s why. AI works by inference. It’s consumed decades of interface design and is extraordinarily good at recombining what already exists. But recombination is not invention.
Pinterest didn’t redesign the grid. They broke it.
TikTok didn’t redesign the video feed. They eliminated it. Tinder didn’t redesign the dating profile. They turned it into a gesture.
Every one of those came from a human insight about human behavior. Not from analyzing existing patterns and producing a variation. They required someone to look at a problem sideways and have the conviction to ship something that initially seemed too simple or too strange.
Could an AI have proposed that swiping on faces would become a billion-dollar interaction?
I doubt it.
The interview question
I’ve been asking my peers a question lately: “As AI disrupts our industry, how do you plan to pivot your career when the work we do is made obsolete by Gen AI tools?”
Most of them freeze.
The honest answer is: the job is splitting in two.
One path is craft. The pixel-level, implementation-focused work that’s defined the profession for fifteen years. This path is being automated, fast. Fighting that is like my old team fighting to stay on Sketch because they’d customized their toolbars. Nostalgia is not a strategy.
The other path is invention. The messy, ambiguous work of identifying unmet needs and proposing interactions that don’t yet exist. This is where the value is moving. It rewards skills design school barely teaches: ethnographic research, systems thinking, behavioral psychology, the conviction to propose something genuinely new. They ones who can see what AI cannot. The unspoken frustration. The latent desire. The gesture that hasn’t been invented yet.
Figma’s legacy
Figma’s real legacy isn’t the multiplayer cursor or the browser-based editor. It’s the proof that tools shape culture. Figma made design collaborative, and in doing so, it changed what it meant to be a designer.
The tools coming next will change the meaning again. When code is the canvas, when an AI agent is your collaborator, when your design system lives in your codebase, “designer” will mean something closer to “inventor” or “interaction architect” or maybe something we don’t have a word for yet.
I don’t know exactly what that looks like. But it feels familiar. That same electricity I felt watching two cursors move on a canvas in 2018, knowing the old way was already over.
The only question is whether we’ll spend three months migrating, or three years resisting.
Want the actual stack I’m running on production work?
The full breakdown. Which tool I reach for when, the prompts that actually hold up under real workloads, where Claude Design, Stitch, Cursor, and Claude Code each fit (and where each one still breaks), and the file structure I use to keep them from stepping on each other.
This is part of my Design Stack Playbook. Constantly being updated as the tools evolve.
Paid subscribers get it below.
Sherizan is Chief of Design at Botim, MENA’s fastest-growing super app. Previously Design Leader at TikTok and Senior Principal Designer at Grab. He writes Design AI Stack, where he shares weekly playbooks on AI workflows for designers.
