Claude Design

I reckon something like this has only been possible to develop because of how homogenous the internet has become in terms of design ever since the glass effect and drop-shadows took over in Web 2.0 and Twitter Bootstrap entered the scene.

You'll get a competent UI with little effort but nothing truly unique or mind-blowing.

Impressive technology, but that old skool artisanal weirdness of yore only becomes more valuable and nostalgic.

For my agency this won't replace Figma or designers. It's just a really useful tool to express yourself and communicate intent.

Before these tools, when a client wanted a specific section built, we'd spend hours hunting references across the web. The output always ended up feeling like a mesh of 2-3 sites, never fully unique. Then we'd burn more time explaining the intent to the client's designers and devs, usually with multiple rounds because words don't convey layout well.

Now we throw a quick mockup together in Claude or Lovable and send it. The designer gets the idea in 30 seconds instead of a 45-minute call, then pushes it further with their own taste and the client's branding.

It's not replacing designers. Most clients don't know what they want until they see it. These tools collapse that feedback loop from weeks to minutes, so the designer actually spends their time on the parts that need human taste, not on decoding a vague brief.

If you look at Figmas stock price, it started falling right at 11 AM as this news was released.

Anyways, this is 100% a shot at Figma, but also catching Lovable in the crossfire. If anybody from Anthropic is reading this, if you keep developing this with features in Figma and other design tools, you'll have a major hit on your hands.

On Notes on the Synthesis of Form, Alexander defines design as the rationalization of the forces that define a problem. You’ll won’t find a better definition. But people tend to think design is the synthesis and its results. This misunderstanding of the role of design and the designer is responsible for all the unfit designs we encounter on a daily basis. Anyone equipped with a synthesis tool and feeling empowered to quickly and cheaply generate forms will almost inevitably become blind to the very nature of the underlying problems they set to solve. They’ll be fitting the problem to the available forms. They’ll skip the understanding, the conversations, the conflicts and disagreements, and happily and wrongly assume a design problem can be solved hermetically, in isolation. They’ll think quality is a factor of aesthetics, when in truth, aesthetics is an effect; nevertheless these effects is all they’ll have control over, as it’s all the tool can do. The tool will hinder their ability to be rational; to see the inner structures; to find the hidden but essential semantics; to create the ontologies that’ll support not only the immediate synthesis, but that will sustain the evolution of the design over its lifetime. They’ll be denied the enlightenment that comes with gradual, slow construction; the only place and moment where innovative ideas reveal themselves. They’ll be impoverished and confuse output with agency. I feel sorry for anyone that will think using tools equals doing design, because of the truly marvelous human experiences that they’ll miss, and that could never be replaced by the shallow pride of empty achievement.

The more I think about it the more this isn't good for design [EDIT], for a few reasons:

- The best design is original, groundbreaking and often counterintuitive. An AI model is incapable of that, it's uninspired, it will absolutely converge to the norm and homogeneity (you see it everywhere now, just scroll on ShowHN and take a look at the UIs) and produce the safest design that appeals to its understanding of the ideal user.

- Good designers will reject this, they prefer to be hands-on and draw from multiple sources of inspiration which is what Figma boards and Canva is good for, also mainly for cross-collaboration. If you've seen how quickly a great design engineer can prototype you'll know that "speed" they advertise in this video is not worth the tradeoff.

- Creatives typically have a very very very high aversion to AI.

- Non-designers will not see a purpose for this tool, basic design can already be done through Claude Code and Claude.ai, I fail to see what this could offer unless they leverage a model that is more creative and unique by default (you can not prompt/context/harness engineer creativity believe me I've tried).

- Design is a lot more than just UI. Tools like this ignore so many other important aspects like: motion, typography, images, weight, whitespace, sound, feel.

Interesting! I wrote this approach up (more or less - extract design system -> make templates -> export) some time ago and I've found it unbelievably powerful: https://martinalderson.com/posts/how-to-make-great-looking-c....

I use it all day every day with Claude Code. I sometimes wonder past code if this has had the biggest impact on my day to day productivity, either having to make do with semi-bad looking reports or have a designer design them (which is slow).

Sort of feel sorry for Figma in a way though, given all the "partnerships" (highlighting their MCPs) and case studies they've done with Anthropic and then they release this. I note there isn't a testimonial from them this time.

I'm surprised how poorly Figma have used "AI" in general - given they were the "gold standard" in taking emerging technologies (WASM etc) and making an incredible product. The Figma Make thing was incredibly underwhelming, I managed to extract the system prompt out and it's basically just Gemini 3 Pro with a design prompt. Perhaps the original team has left?

They are extremely exposed imo. While all the UI/UX designers will continue using it for the forseeable, I strongly suspect a lot of their (A/M)RR was coming from extra seats for PMs, developers, etc to view and export and do commenting on the files - not core designer usage. I think a lot of this just won't happen on Figma as much.

My feedback for whatever it's worth as a 25yr design veteran.

* Massive token usage, some small tasks burned through $50 of credits and did not offer $50 of value.

* Terrible at logo work. Comically bad. This is something that is "hard" so it could add great value if it could deliver.

* Repeatedly forgot prior feedback - when iterating it would re-implement prior iterations after being told why we didn't want that result which made for a very frustrating UX.

* Prone to adding visual clutter - kept adding extra elements that look "pretty" but add no value to the user.

* Seems better at "pretty" vs user focused / UX.

* Did not do a good job at using my existing design / UI library

* REALLY wanted to start from scratch. Could not be coaxed into designing part of an application, it wanted to redesign the whole thing.

Reading, writing, thinking, code, design jobs are gone. Looks like only onlyfans remains. How long before AI can take over onlyfans?

It really feels like Anthropic's product area is extremely overextended at this point. If they want to extend themselves horizontally in an unlimited fashion, they will need unlimited focus, and agents can't supply that. Things will fall through the cracks. Why should I believe that Anthropic will care about this product in 2, 3 years? Whereas I firmly believe that Figma will care greatly about its product in that time

For me it was the missing piece when working with Claude Code. I am a PM by formation so neither do I know how to design nor do I know how to code but I am pretty good at describing what I want and why. I just played with Claude Design for a while and it made it really easy to explore different solutions, reorganize the interface, adjust little detail with the "comment" function, move buttons around, etc. Then export to Claude code including the design system, and I spend way less time writing a spec and can focus more on corner cases and the ugly details. 2 years ago I still had to hire a freelance designer and a developer for small projects, now for the fraction of the cost I am totally independent and can iterate as much as I want. We always mention that "the design is not unique" or "the software architecture is not clean and the code to verbose" - I get it I managed Series C startup product teams before I got sick of the VC shit show. Now I am working mostly with lifestyle businesses and SMBs that have the ambition to be profitable - and average is good enough for them. They gain access to custom designed software for specific use cases which was completely out of reach for them 3 years ago. Custom solutions meant working with mediocre, overpriced agencies creating "solutions" with Wordpress. Anything I can do with the Claude stack is on higher level at a fraction of the cost. And as long as it works and looks good those business don't give a ** about unique design and scalable software engineering.

I see a lot of responses here taking the purist line: that it's not real design and customers will know the difference. I suspect it's close enough in many cases that customers won't know or won't care. Likely it will have a big impact on design employment.

I've been building a similar tool since Tuesday with CC and got very far, More thought out features and interface then this. Applications have no moat, when you can build it in a week.

Really hope Anthropic didn't notice my ingenious work and quickly copy it.

"create polished visual work like designs, prototypes, slides, one-pagers, and more."

I use Opus to generate Typst for that and I'm already pretty happy with that approach. It gives me a degree of control I do not have with other methods, because

1. Typst is really powerful

2. Opus is really good at surgically modifying Typst

I basically never look at the Typst code for this. Telling Opus visually what I want changed is usually good enough.

This explains why Mike Krieger left the board of Figma (https://techcrunch.com/2026/04/16/anthropic-cpo-leaves-figma...)

Let's not fool ourselves: their goal isn't to build a design tool, it's another training tool for a field where training data is hard to collect. We collectively reinforce predictions to sharpen the models. The pattern is clear across all their products. This is training for future one-shot generative UIs. UIs are already generative; this will scale that up to a world where applications are mostly UI-less.

This is cool!

Seems like Claude is actually building almost like a layered Figma wireframe that you can do fine grained adjustments afterwards (e.g. adjust font size).

Interesting that Canva provided a quote of support. I'm not familiar with the differentiation, but it seems like this will directly siphon customers from Canva, right?

What’s interesting here is that with AI, all our interfaces should evolve away from previous generation rigid forms / buttons / tables etc. towards something more fluid / dynamic / “natural”. Yet all the AI coding is geared towards producing more of the former.

I'm a max plan customer, use Anthropic products A LOT and am generally impressed with Claude Code. But this is not even close to being ready for release. Below is the transcript of me trying to initialize a design system. Pretty disappointing, this clearly wasn't tested by humans.

Exact Transcript as follows:

-- Claude: Let me fix these precisely: <empty>

-- Me: ok

-- Claude: <empty>

-- Me: hello?

-- Claude: <empty>

-- Me: there's still some issues with 01 live and 02 - your business.

-- Claude: <empty>

-- Me: hello?

-- Claude: Sorry about that. Let me look at those two and figure out what's still wrong. <empty>

--- Me: hello?

-- Claude: Screenshot _illo_check.html Viewing image illustration-pillar-1.svg Viewing image illustration-pillar-2.svg <empty>

Import/export anywhere not including Figma is diabolical. Otherwise it looks fantastic!

Why on earth is Canva parternering here? This is literally eating their world.

It's interesting how OpenAI and Anthropic effectively mass dumped a bunch of similar features in the last two days.

I wonder what other features they're cooking right now.

404 Page not found when clicking on their link https://claude.ai/design at the end of the article! Vibe coding to prod, gone wrong?

So how much of this is fully generated vs AI running through all the knobs on template widgets?

Is that globe made from whole cloth or is there a bespoke "telecom globe" widget that it dropped in? Could I ask for mock up of molecules with the same fidelity of knobs, down to nucleus size and such?

The labs team absolutely cooked with this. As a designer who's been using Claude Code a lot to make better prototypes, I still go back to mockups for comparing many iterations, collecting precise feedback with comments, and documenting decisions for decks or sharing with other departments like product marketing. This seems to solve for all of these use cases (or at least start to).

It's also just a beautiful product. The interaction model, styling and integrations via exporting is all super thoughtful

When Anthropic's CPO left Figma's board this week, that was my first question . Oof.

Remember, every product they release expands the scope of their non-compete clause, and they like their lawsuits.

The Anthropic team looks to be eating all the usecases and application layer. I personally know of many figma + AI startups that are going to feel shaken up with this launch.

Anthropic has distribution on their side, their engineers are excellent (I have ran with them across the ggb in the past and they work 12 hours plus a day regularly.)

I think what actually might be slowing them down is the public releases and pr lol, not ideas or execution

I don't really care about the web builder, a better slide deck creator I'm down for with MCP capabilities, pulling in things like Atlassian & Dyantrace metrics for slides would be nice including github issues etc.

Lovable was a TailwindCSS recombinator, that’s it.

Lately it is more and more ShadCN as well.

TailwindCSS is a masterpiece but ironically doesn’t really get its fare share while “Build on top of TW” frameworks make money.

TailwindCSS is the final evolution after all other frameworks always had its benefits but also massive limitations.

BEM anyone?

TW is really elegant a new paradigm in its purest sense and brilliantly executed. No wholes could be poked in it for years and the extensibility shows, how brilliant it is.

Bootstrap will always be held dearly but it was about browser quirks etc first. Important milestone but stands no chance against TW.

Maybe I am using it wrong but it feels much closer to Lovable than Figma. I was expecting this to feel like the two products combined. Certainly better than Lovable though, but a little disappointing.

I think it’s clear that Anthropic are leading the industry right now and I believe it’s because they are better at using their own tools to develop software than anyone else. I suspect that trend will accelerate.

Unfortunate that linking code from your computer doesn't work with Firefox

Very interesting though

Good for crunching out some prototypes, ideas and getting inspirations I guess. Two prompts - the initial one and one refinement - took about ten minutes and used up 90% of the token budget. I wonder what the real costs are. After the IPO, they will no longer be able to subsidize token costs. The question will then be whether it's still cheap enough just for prototypes, ideas and inspiration.

This but attached targeting a 3D printer.

Really interesting response to Google's Stitch - and seemingly a better alternative given some of the features shown in the video. If everything actually works at least close to how it's advertised, this'll be useful. I'm sure it's no Dieter Rams, but it wouldn't be a surprise if it's already better than many devs at design work.

I threw my sales deck at it and asked it to implement our brand guidelines (attaching that as a PDF). It did a great job and then began giving me internal server errors... I'm going to assume this part of their model farm is totally overwhelmed.

I've been spending the last two days building a large number of mockups for a new product. Literally the last two days.

I'm wondering how i can CONTINUE that in this design thing, can i import something? Because they show it the other way... you can start and edit, and then export to claude code.

Until then, I guess it's back to just using CC

The design process was completely dictated by Figma. After the demise of Adobe XD, Invison etc they were the only option. Happy to see alternatives entering to save us from the curse of Figma !

https://getdesign.md/ provides more accurate design system extraction than Claude design. Could be use vice-versa

I think UI quality is going to stop being as important when anybody can just generate an "average" UI that is good enough in minutes.

Ultimately, this really just shifts the focus towards product design and ideation rather than UI design.

> voice, video, shaders, 3D and built-in AI.

As someone who's thinking about side project-ing a game, this caught my eye.

I am curious to explore what Claude can yolo in terms of a retro style indie game... One who's audience might only be me.

Unless you want something that looks like it's designed by Anthropic, this is still pretty shit. Amazingly "AI" hasn't replaced the very first target on their radar - design.

Having generated ~250k web design images the past few months, I've concluded generative models, circa 2026, still suck at it. Presumably because the difference between an 'OK' design and a 'Great' one is pretty darn small and far too nuanced. That said, Imagen easily takes the cake for workable design creativity, but even then, it takes 1000ish gens to get something decent, maybe 200 if you aren't too picky.

I've been using stich from Gemini, and just plain zAi for helping redesign my website. You can use the generated code to copy and paste the design to fit your own templates, but that's a pain. Unless you are ok with using tailwind and the dozen or so classes on every element and don't want to edit anything.

What I found valuable is the design.md that was produced. It's a guide for building each component. So using these tools becomes akin to PSD to html we used do. At least that's when I find them most effective.

I tried and not impressed. Even latest and greatest LLMs still have very poor understanding of geometry and numbers.

They state the link is claude.ai/design, which currently goes to:

Page not found Claude can help with many things, but finding this page isn’t one of them.

when logged in.

It's funny seeing the Co-founder of Canva commending the product. Yikes!

This app is pretty slick, this will funnel a huge number of customers away from Figma + Canva imo.

So.. this is why Anthropic CPO left the board of Figma

Very mid. If you have any experience building your own UI kit, this will just slow you down.

I am not an engineer, I can't look at code and determine if it is good, performant, or elegant. However, I can look at designs and make a judgement. I'm curious to see how Claude Design changes how I think about AI and its capabilities.