Claude Design
anthropic.com
anthropic.com
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.
If I'm building out an internal tool for, say, a hospital lawyer to search through malpractice lawsuits, I want my tool to be the most familiar, obvious, least-surprising UI/UX possible. Just stay out of the way and do what it's supposed to do.
The trick is, of course, that the human is still responsible for knowing when homogenous is fine, or when there's real value in the presentation. If you're making a website for, say, a VST plugin for musicians, your site may need to have a little more "pizzazz" to make your product more attractive to the target audience.
90+% of attempts at making a truly unique or mind-blowing UI produce a mind-blowingly bad UI. For 0.5 seconds of wow factor, you've added substantial unnecessary friction. Outside of art projects where that wow factor is the point, it really should not be attempted, most certainly not by someone without the appropriate skillset.
The old skool artisanal weirdness was not a purposeful stylistic choice, it was a bunch of people trying to do the best they could with crappy tools. There may be some je ne sais quoi which is lost with the shift to mass adoption, but the reason for the mass adoption of these particular design trends was that they were objectively superior.
Which is exactly what I want. Do you have any idea how hard it is to get a competent UI?
Why do people celebrate consistency and uniformity in desktop apps, wanting to crucify developers for not following platform idioms and guidelines... and then suddenly want things that are "truly unique" or "mind-blowing" or "artisanal weirdness" when it comes to a web app?
A competent UI with little effort is a godsend.
This is exactly what I want in a UI.
The hilarious thing is that I would be willing to bet than in a decade, it's STILL a massive shitshow in enterprise. That's because the problem with enterprise software is not that good design is all that difficult to pull off (it just requires caring!) It's that the people making enterprise software have terrible taste and can't even see (I am convinced) that the thing they built is ugly and hard-to-use.
I guess post IPO, after the insiders cash in out of lock period its irrelevant.
Or “2000s aesthetic” for something before Web 2.0 (although you’ll get a generic 2000s aesthetic unless you provide more detail).
Sure, some prototypes will be spun up more quickly. But if this was a real problem large companies faced it would have been solved in software already.
AI companies: "good news, everyone! We've automated all those steps so they're even easier to generate!"
I think the same thing is happening in physical construction. Ah, I see you've designed a new box with four primary color tones and slightly offset vertical lines to break up the windows.
When you say old school artisnal design and weirdness do you mean something like this: (shameless plug, but relevant to design)
https://swellslots.com (surf forecast site)
The design for this was literally "90s Arcade / street fighter 2 look"
Funny enough without AI, i would not have been skilled enough to make the graphics (background, logo etc)
This comment is just a rehash of the increasingly outdated and incorrect assertion that LLMs can't possibly exhibit any creativity -- and it's also incorrect.
If you're yearning for "old skool artisanal weirdness of yore", look up the trend on Twitter a month or two ago of people asking Claude to make YTPs. They ended up very weird and artisanal in a way distinct from how any human would do it.
In fact, humans waste countless hours trying to figure out what is what and how things work, just because there's always some designer trying to do something nifty. And by "designer", I don't necessarily mean professionally trained designer - although the pros can be given to trying to make artistic rather than functional interfaces.
If you are an UI designer and want to create art then fine do that in your spare time. But at work be a professional and make the UI predictable and functional above all else.
but does it still exists? Even without AI everyone is utilizating the same css frameworks, same libraries and templates... design is pretty much boring these days. CSS Zen Garden anyone?
In a direction where the AI model basically serves you everything live. No sites, no front end, just databases and model embodying them.
I mean why even code anything in the future where it is cheap and fast enough to just come up with everything each time based on each user need.
I am not saying it’s good but it’s lazy. And if one thing is for certain is that laziness prevails. Some even mistake it for progress.
But then, is human programming language really the most optimal way for an ai to steer the silicon? Some kind of bare AI OS with kernel, drivers and there in the middle a fat specialised asic ai chip to orchestrate everything.
I think it's because Steve Jobs killed Flash.
You might just as well bemoan the homogeneity of Windows 95 apps. All those gray buttons in the bottom right of windows.
It’s 2026 and every web application has a different menu layout, date picker, etc.
Designs have been settling on a local maxima. If you are aware of a better hill to be climbed, please do let everyone know.
The shelf-life of unique and mindblowing has reduced to a week (being generous) before it's copied by slop artists looking for a resume booster or funding, and months tops before it's part of training data for everyone. Unless you find it in that small time window everything will seem homogenous.
It could just be a systemic result; unless you deliberately take the lonely road to parts of the internet where other people aren't, you will not see unique and mind blowing things. Which by definition you can't source from a place that has a lot of users, like social media or popular forums.
And rounded corners, of course! :)
This is most every corporate website.
p.s. Perhaps “quirky” is less because it’s simply not fulfilling? Too often it’s visual gaslighting pretending to be design?
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.
Except it is. Plenty of places will say this is all good enough and not hire, or even lay off, the UI/UX person. I've seen this firsthand.
This is just a really cool way of building.
I'm impressed. I tried Google Stitch but it was slow and useless. Sad, because Gemini has a pretty good creative flair, ironically enough.
If every designer takes less time to do their job, you need less designers. There’s no getting around that simple math.
2. Long term you can expect the minimum bar for aesthetically pleasing design to be raised and there to be overall less demand for human produced generic design.
3. This will mean all designers get pushed into the same corner or complex, unique, uninferable design and trying to fight it out.
Now, if I could only get a model to draw arch diagrams....
This is also true for entire applications. I vibecode apps in 2 days then say: is this what you want? Then they are enthusiastic and I will say that it will take 2 to 4 weeks to properly create it. They are always confused and then I start teaching them the conceptual basics of how apps are built and what corners are cut. Clients usually listen because they know we’re near the finish line
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.
Figma is targeted towards designers who create thoughtful design systems and cohesive UIs and who don't code, while this is targeted towards vibe coders who can't design. Two different circles that intersect to some level.
But like you said, if anthropic adds the tools in Figma, only then they can can take customers from Figma IMO.
https://stitch.withgoogle.com/
I'm now pasting all my Stitch output into Claude Design to see what happens.
edit: First impressions are great. It asked me a ton of really great questions about my design aspirations and direction, which were incredibly relevant and insightful. Waiting to see what it makes.
edit2: It did astonishingly well with the first design pass. Really outstanding. This is probably going to be my primary prototyping tool until the Next Best Thing(tm) drops in a few weeks.
They're down 80% over the last year. Ouch.
Figma actually put the work in to make a great product that performs well and offers anything you could imagine to design just about anything you need, with AI integrations and deep manual editing to sweat the details.
Design work is already under a lot of pressure. I work with somebody that has an industrial design background and he's having a lot of fun with AI tools. There is still a need for good designers. But not to do a lot of the low end design work that has been common in a lot of front end teams. That stuff was always a bit questionable in value. I know some decent designers that were actually getting bored with that type of work. It's very repetitive.
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.
Those partnerships and the MCP were intentionally always watered down. It was purely a play for some cheap exposure without providing anything meaningful.
The very obvious thing for the MCP to expose, that everyone asks for, is to be able to create and edit Figma designs. You can't, likely because they're scared it will kill their product. It's one way: Figma->Agent, no Agent->Figma. They will come around to this one day, potentially when it's already too late. Will be interesting to see how long they wait.
their seats system has always been brutal it’s extremely easy to have the seats balloon if you’re not careful and if they’re yearly there is only a 30 day window a year where you can cancel them when the banner to do so appears.
Nope. Figma Make first renders an HTML/React app with your design. Then you could convert to a Figma design file if you have a pro plan. Extremely underwhelming.
There's hardly any difference between using Figma and just designing it with Codex and Claude Code. And now, Claude Design seems to get it right.
- 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.
Designing a user inteface involves thousands of small decisions. When trading off pros/cons for each of these decisions, in 99% of the cases, the right answer is ‘optimize familiarity.
That’s why Android and iOS look the same, and why the small differences between them are where contention happen.
If you adopt existing patterns, your users would be instantly familiar with your app, and the design will not get in their way.
If you want to make a GUI, it should be familiar. Extremely familiar. It shouldn't invent new ways to interact most of the time.
It is well-known that "intuitive" in UX almost always means "what I'm used to". If you're regularly "innovating" in UI design, you may be making the product harder to use, maybe much harder to use.
It certainly isn't unheard of for new ways to interact with computers to be better than the old, but they are usually tied to new physical aspects of our tools: Touchscreens needed new ways to interact, and maybe there's still some room for creativity there, but not much. The mouse obviously required innovative ideas for several years. But, also, the odds of your wacky new idea being the right way to change how people interact with computers are pretty low, unless you're working at FAANG and have a UX research team and budget to test it.
You can get creative in how it looks, but you cannot get creative in how it works.
Overall after being laid off in January and a 17 year UX Research/Design/Dev career Im starting school in my early 50s to change careers.
"Good designers will reject this."
^ Famous last words.
I have no idea how everything will play out, but this sounds a lot like the people saying "good programmers will reject this" six months ago.
Quite apart from anything else, it ignores the fact that—particularly within large organisations—designers (and programmers) frequently have very little say in the matter.
Jeez I hope fewer designers think like this (and if it's a traditional wisdom among designers, I hope fewer designers in general.) Perhaps web apps will stop moving their icons and buttons around every six months.
Not everyone is looking for unique design, 70% of the web is still using Wordpress. I would say majority prefer familiarity and appreciate uniqueness.
I guess that kind of thinking got us liquid glass - which everyone hates.
Until we have embodied AI's with eyes and hands that provide good enough approximations, the aspect of design bottlenecked on human experience will stay bottlenecked.
most of those "breakthroughs" were just constraint hacks. no room for a reload button. no room for another menu.
enterprise buyers don't pay for counterintuitive. they pay so the new hire finds save without training.
You’re talking about art, not design.
If you want to talk in absolutes, I'd say the best design is the one that results in the desired behaviour of your audience.
Even the most deluded AI bulls don't say that AI is even meant to replace the best that humanity has to offer
While Great design breaks the mould, Very Good design is about surfacing the most expected outcomes for any action which reduces friction and lets people get work done. And this generation of Generative tools is very good at identifying the most common/most expected response to a prompt.
This is for non-designers to crank out slop with less effort. They can still be swayed by all the shiny knobs to feel in control.
What if you don’t give a shit about design and it’s a means to an end for a project that involves something different that you do care about?
I'm an engineer who also loves design. I've read a lot of the books (including the one referenced), I know some concepts and terminology, and I understand the general process — but I'll never be a professional designer. My knowledge is limited, and I find most design tools so complex they actually get in the way of problem exploration and creativity.
For people like me, this tools removes the friction which actually prevents me from being more focused on the valuable parts of the design process. I can more easily discover and learn new concepts, and ultimately spend more time being creative and exploring the problem space.
I think the challenge will be everything else the person will be doing. Will this person also try to coding? And financial management? And marketing? And operational planning? Just because there are tools out there for them to synthesize implementations of that. If so then they wont be able to get good at any of those. But i think the backwards pressure from failing at those things will bring it back to a stable equilibrium where you have specialists who are good at the abstract ideas of their field leveraging these things as a new abstraction layer of work, analogous to the compiler
I think itll be fine
However, that’s not to say that many designer jobs will be going away, simply because for many cases, cost beats quality. We’ll just have more things with a much lower quality.
You can compare it with mass manufacturing. While some things are better had than not, even with low quality, we’d probably be better off with some things made to last, in lower quantity. But for 99% of the population, e.g. low quality clothing is the norm.
And if it’s LLM the prompt or the rework were very good because I really liked the flow and clarity. That, or you’re a really good writer ;)
This speed and variation wins for me. But yes without a designers eye laziness can get lost in slop design too..
To me the value of Gen Ai is an accelerant (not slop factory) for ideation and solutions not a replacement of the human owning the process.. but laziness ususally wins
when people wax philosophical/poetical about what is essentially capital production already i'm always so perplexed - do you not realize that you're not doing art/you're not an artisan? your labor is always actively being transformed into a product sold on a market. there are no "marvelous human experiences", there is only production and consumption.
> They’ll be impoverished and confuse output with agency
ironic.
They realized they have no product or ground to stand on. Once such model drops and once chip manufacturers catch up with demand, they are dead, if their only product is inference.
So OpenAI decided to do weird things like buying up all the hardware that exists or will exist in the next 2 years to buy time to build the product. Then launch things like Sora, ChatGPT shopping, ads etc. They seem to be struggling with this.
Anthropic, being late to the game of hoarding up all the hardware, decided to "buy time" by hiding CoT, implementing KYC (especially for Chinese users), to delay the efforts of distillation. The products they build in the interim are SaaS clones designed from the POV of AI agents and tight integrations with their models.
And it seems like Google is just sitting aside, watching things unfold, since their business model doesn't stand on inference.
The most likely scenario is that OpenAI and Anthropic will still crash and burn when such open model is released.
Figma's survival is still questinable though. Most likely scenario is likely that there's going to be an open source alternative that has AI integration at the core level, rather than an afterthought.
Anyone remember Google's social media platform??? Google Plus?
This is a good era to be in! Its the era of product experimentation.
As long as you realize that 90% of the products will not be supported long term if it doesn't contribute to bottom line revenue, then just appreciate it for what it is, a bunch of smart people trying to create useful products.
Just don't be surprised if Anthropic goes the Google route, which is shutting down the majority of the products that are too small / not successful enough to impact their revenue.
Keeping the hype alive through to IPO is critical now.
There's no reason to believe Anthropic will stop caring about this product--they're not Google [1] after all.
> It really feels like Anthropic's product area is extremely overextended at this point.
I don't think so. They have one core product: the Claude model; they're enabling different ways of accessing it. Claude Code for developers, Cowork for general business tasks, and chat for consumers.
This is their first graphic design product, but it fits nicely because once you create a prototype, you can hand it over to Claude Code to make the website, mobile app, or whatever.
The advantage Anthropic has is their ecosystem. A Claude user will be way more productive using Design because all of their context is with Claude; other AI tools don't "know you" the way Claude does. Claude already knows your style and your preferences; it's much more likely to create designs you'd like.
When you go to an AI you don’t normally use, you essentially have to start from scratch.
* 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.
OK but what we really want to know, what's it like when it comes to drawing pelicans riding on bicycles?
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.
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?
The big question is, of course, how invested will they (the companies) be in their products? Will it be a re-run of Google where far too many products end up being scrapped after a year or two?
My 76yo Dad just used Claude Design to make a simple commercial tenancy/lease management CRUD app. We handed what he built to Claude Code to implement within my existing business tech stack. It perfectly followed my coding & testing playbooks (basically a multi-file CLAUDE.md with prompt & command hooks to evaluate conformance). It works… exactly as my Dad imagined.
Now, mind you, my Dad had some outdated UI expectations (he asked Claude Design to style use a Windows 98 aesthetic!), but my point is: we just built a fully-functional, deeply tested, domain-expert-designed app, in less than a day.
This is a success story I've been hearing more recently. Restaurants, contractors, plumbing, 1 person startups... I'm wondering if this is because the barrier to entry is now lower - or if these tools are actually moving work away from small software teams or individual devs.
IMO this is the crux of the "AI Eating SWE" scenario (along with other knowledge work...) I'm sure it's a little bit of both. If this was something you were going to pay a designer and a developer for, it changes the outlook.
From my perspective, it feels more likely that with cheaper software we'll see a rush of people building their own, but once it gets sufficiently complex it then needs to be maintained, or improved, and it becomes more work than the initial weekend POC.
Previous comment with the prior 3: https://news.ycombinator.com/item?id=47794419
I wonder what other features they're cooking right now.
Why would we want to move away from hard fought UX design lessons? Dynamic and fluid UX is infuriating.
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
What a toxic workplace :/
What? In my experience people who are good at their job can get it done in a reasonable amount of time. Working 12 hours a day is obsession, no competence. There can be overlap, but there is no causation.
The alternative is to not hop on the AI bandwagon, or run an "also ran" AI story, and both those scenarios (I expect) game out worse given the current zeitgeist.
Another thing: I realized how much I hate waiting for Claude to finish its thing. With UI designs, a quick interaction loop between tool and user feels much more important than with code.
Here's the prompt as of around release-time yesterday. You can verify in your own network requests.
https://gist.github.com/mcrowe/9da081f52e0740886d39e730852db...
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?
It's also just a beautiful product. The interaction model, styling and integrations via exporting is all super thoughtful
Deriving a bland average of creativity is the saddest thing you could do. I don’t even enjoy design and I find this offensive.
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>
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.
As a dev manually typing I loved tailwind for sure, with LLMs not so much, and bootstrap in particular nails it the best IME. and yeah one can customize bootstrap quickly to look however it should, just tell your frontier LLM of choice your wishes.
This app is pretty slick, this will funnel a huge number of customers away from Figma + Canva imo.
Very interesting though
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
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.
I have been doing fine just instructing Claude code to use Tailwind and reference design documents
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.
Page not found Claude can help with many things, but finding this page isn’t one of them.
when logged in.
half the design problems I've seen weren't bad taste. they were bad communication between the person who knew what they wanted and the person who could build it.
> You've hit your usage limit. Claude uses a different usage limit. Resets Mon 12am
It's Tuesday. What are we doing here, Anthropic?
This was also the last day until my subscription ends. Good riddance.
Edit: I see they have a new token tier 'Claude Design' so that's good.
Anything but that
Ultimately, this really just shifts the focus towards product design and ideation rather than UI design.
Fed it my figma file to it and creating a design system. And yeah, it looks like it, but it's still wayyy off at the same time
Maybe AI is not good at everything, yet.
That link is redirecting me to https://claude.ai/404, anyone else?
Can't even test two designs. No idea if PDFs used up so much budget.
If you’re confused about why everyone is shipping their own canvas tool - this is what I wrote when I reviewed Stitch from Google in my newsletter:
“every SOTA (State-of-the-Art) model can already do this. Give it a prompt, it'll spit out an HTML design. Ask for 10 responsive variations, you'll get them. Stitch is a Ul and context harness on top of Gemini, in the same way Claude Code is a harness on top of Claude's models. This means every Al lab will likely ship their own version, and they'll all interoperate because at the end of the day it's all HTML and markdown.”
More generally, this is a competition of where the product development work starts and lives. The business value will accrue to those who become a destination, not a plugin.
AI can now power a new sort of tool that supports the entire process (not just coding or just design). So there’s no reason for Anthropic or any other lab to give that up to another tool.
The design problem to solve post-ai isn’t this it’s how the space for thinking fits into all this, getting to the end result slower so human ideation can play out. This is just optimized for the first generic output + tweaks.
Unfortunately it's going to be a tough few years until that happens, where it really does feel like the idiots are winning.
THE IDIOTS ARE WINNING
Reusable components. Shared styles. Auto layout. Variants. Design tokens. So many useful plugins! Interactive prototypes. Dev mode handoff. Versioned libraries. A single source of truth keeping designers, engineers, and PMs speaking the same language.
It's fucking bliss when you use it right. And best of all, anyone on the team can build with the legos the designers gave us!
Teams finally started treating the design system like infrastructure instead of decoration.
Then Figma Make showed up.
It generates pages that ignore your components, skip your tokens, and treat every screen like a fresh snowflake. Looks fine in the mockup. Lands like a brick on the dev team. Now every page is bespoke and every handoff is a rebuild. Fucking sucks.
We had it all figured out, then we fucked it up.
AI was supposed to accelerate momentum. But it just so completely lacks maturity. AI Tools are dragging teams back to 2010, when every page was a Photoshop file (with way too many layers and shitty names for them) and none of the designers can agree on what radius to assign to their buttons.
Good design systems are a discipline. If your AI tool doesn't respect the library, it's not a designer. It's an intern with a Molotov cocktail waiting to destroy your productivity.
I haven't used Claude Design yet, I'll try it, but I LOVE Figma, and I hate Figma Make. I don't have high hopes for Claude here.
> do you see our current html
Hi-fi design Interactive prototype html
> do you see our current html
Hi-fi design Interactive prototype html
● Claude Yes — I can see your html/ folder. It has 7 files:
files-list.html math-result.html rows-view.html table-view.html text-editor-doc-view.html trending-topics.html unique-result.html Want me to open them up and take a look at what's in there? And what would you like to do — polish them, turn them into an interactive prototype, build something new on top, or something else?
> yeah in table view i'm thinking about how to deal with cells that may be big. i guess we want to do something different than excel or sheets in that auto expand rows with cells that contain big values. we can show like the first -- what does twitter show, 280? so we can show 280 chars and then [...]
● Let me take a look at the current table view to understand what we're working with.
Got it — I see the current table view. Right now every cell is clamped to max-width:220px with white-space:nowrap and text-overflow:ellipsis, so long values just get cut off at whatever ~30 chars fits the column. You're thinking about the opposite end: what if a cell genuinely holds 2,000 chars of text? Neither pure clip nor Excel-style row expansion is quite right.
Before I start sketching, a few quick questions so I don't guess wrong:
> Questions answered: - truncation_threshold: ~280 chars (new tweet) - expansion_ux: nothing right now -- it's not interactive - row_height_policy: Grow freely like Notion/Airtable - content_types: Not sure yet - indicator_style: [...] at the end of the text - newlines: Render them (row grows) - copy_affordance: no interaction right now - column_width: Fixed width, all columns equal - variation_count: 2 variations - aesthetic_direction: Same bones, but let you push it a bit
● Got it — so: non-interactive, rows can grow freely, 280-char cap with [...], newlines render, same bones but push it a bit, 2 variations. Let me sketch this out.
Set up variations file with two table treatments V1: Notion/Airtable-style free-grow with [...] cap V2: pushed aesthetic variant Wire both to the same sample data w/ long cells Let me peek at a couple of the sibling files so the variations stay in-family with the rest of the widget set.
Good — now I have the visual family. The shared vocabulary across widgets:
#f5f5f3 page, #fff card, #d0d0cc borders, #f0f0ec headers System font, 12–14px Subtle alternating row tints, no drop shadows, flat corners Color used sparingly; #666 for secondary text My plan for the two variations (side-by-side in a canvas so you can compare on the same rows):
V1 — "Notion-ish, stay in family"
Keep current palette, borders, zebra striping Rows grow vertically as needed; white-space: pre-wrap so newlines render Cap each cell at 280 chars; if longer, slice to 280 + […] inline Same fixed column widths, everything else identical V2 — "Same bones, pushed"
Tightens the grid (hairline borders instead of panels, more whitespace, denser typography) Column rail with sticky row numbers Soft fade on the bottom of ultra-tall cells instead of mid-text […] when content is really long (hybrid: char cap + visual) Monospaced tabular digits for row numbers; type column ⌾ / ▤ markers subtly hinting content type; column width slightly wider for breathing room Let me build it.
Now let me build the two variations. I'll set up realistic sample data with a mix of short values, tweet-length values, long-long values, and ones with newlines, so the behaviors are visible.
Now the two table components.
Clean. Two variations on the canvas, both rendering the same 7 rows so you can compare directly:
V1 — in-family. Your current widget, with white-space: pre-wrap so rows grow, newlines render, and a soft grey […] appended when a cell goes past 280 chars. Row 3's summary (double-long prose) and row 4's URL show the cap. V2 — same bones, pushed. Hairline borders instead of filled header panels, monospaced tabular row gutter, column letters as uppercased small-caps above the header names row, tighter typographic rhythm, cells > 280 → […] legend in the footer. Row 7 shows how newlines render naturally. Both slice at the nearest word boundary when one is within ~40 chars of the 280 cap, otherwise hard-cut — so […] never lands mid-word.
A couple of things worth calling out, not changed:
280 is pretty generous when a row has multiple long cells side-by-side — row 3 is ~2 cells × 280 = a very tall row. If that ends up being painful in real usage, dropping to ~180 or adding a per-row max-height with fade might be worth a follow-up. Neither variation is interactive per your answer; there's no click-to-expand, hover, or copy. Easy to bolt on later. Fork verifier agent Both variations are live on the canvas. Let me know which direction feels right and I'll fold it back into html/table-view.html." -----
It's basically similar to their Artifacts system in a harness I guess
Really hope Anthropic didn't notice my ingenious work and quickly copy it.
You talk to it, it consumes "usage" and no design system created.
Had a similar experience with their online code sessions.
All this slop generated code is so freaking bad. We'll get drowned in so much slop code that at some point only these garbage machines will be able to "work" with it.
Part of this weirdness is the continual relativism of design. A taste-meme is good or cringe only relative to the prevailing social environment, never itself. An AI can never do "design", properly understood, because design is the work done by a reluctance motor, spinning endlessly in a Sysphean quest to align itself with a moving magnetic field and producing torque by side effect.
All efforts like this can do is capture the field alignment at an instant in time. It cannot do work. It cannot produce motion, not as long as its weights are as fixed as the field lines of a neodymium magnet. The instant AI design is good, it becomes bad through the act of becoming good.
Producing work through motion of taste may be one of the last human endeavors to be absorbed.
>NEVER use generic AI-generated aesthetics like overused font families (Inter, Roboto, Arial, system fonts), cliched color schemes (particularly purple gradients on white backgrounds), predictable layouts and component patterns, and cookie-cutter design that lacks context-specific character.
> Interpret creatively and make unexpected choices that feel genuinely designed for the context. No design should be the same. Vary between light and dark themes, different fonts, different aesthetics. NEVER converge on common choices (Space Grotesk, for example) across generations.
[1] https://github.com/anthropics/claude-code/blob/main/plugins/...
It's not X, it's Y! all over again?
With that said, this seems like it's just claude code + simplified devtools in a container? Will need to spend more time with it to see how EG commenting influences things, but 5 minutes in, this seems like it's needless formalization on top of how I already used claude for deisgn
Semi-relevant XKCD: https://xkcd.com/1425/
This will fail because it's already a forgotten side project within anthropic, and anthropic also has pretty bad product DNA as a company. Their headcount is already too large and the culture is already set. They grew revenue so fast they speedran the stage at which you could build software product chops into the company culture (think Google circa 2008 vs. Google circa 2018).
They should focus on what they're good at: the actual AI models and B2B sales. Let OpenAI play early Google and churn through 100 different consumer product experiences to see what sticks, they're better positioned for it anyways.
Imagine if a designer were hired to custom design the lightswitches in every building. We need to get back to off-the-shelf interfaces and stop wasting smart people's time reinventing UI widgets.
Go ahead and roast me.