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 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 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.
Everyone else is already pointing out how competent over unique is purely a positive, so I want to criticize the other implicit assumption here.
This comment is just a rehash of the increasingly outdated and incorrect assertion that LLMs can't possibly exhibit any creativity -- and it's also incorrect.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 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.
> You'll get a competent UI with little effort but nothing truly unique or mind-blowing.
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.
Having just checked my child in for their doctor appointment, 90% of web software would be dramatically improved by using very boring best practices and readable and accessible web practices.
Design is primarily craft, not art. The designers who believe they’re artists are often dangerous and toxic, coz they feel the urge to inject their “art” into everything they touch. I say that as a professional designer.
I know what you mean.. and me as traditional none designer have been using bootstrap css since the start. As usually my css would look like an engineer trying toso design.
When you say old school artisnal design and weirdness do you mean something like this: (shameless plug, but relevant to design)
Screen size is probably responsible for a vast majority of the homogeneous of the internet; but that a good thing. The space has matured and horrible experiences fewer. There’s a fine line between creativity and bullshit. Less bullshitting is a good thing.
p.s. Perhaps “quirky” is less because it’s simply not fulfilling? Too often it’s visual gaslighting pretending to be design?
Most day to day apps and websites should be boring and usable, not truly unique or mind-blowing.
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.
The vast majority of people using UI's want predictability. Not "guess how this UI works!" games where you have to click on things at random to figure out how the UI works.
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.
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.
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.
If you want to be creative, you should make art. I love art. I think it's a great idea for people to make art.
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.
> The best design is original, groundbreaking and often counterintuitive.
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.
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.
And another step toward a world, where product managers/owners/whatever and other boring people can generate what they once needed creative, passionate and skilled people for. Go ahead, its just the natural evolution of extreme capitalism.
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.
Judging by Anthropic's track record for sloppy, buggy software, I can't see this taking off quite as well as people might think, when compared to Figma and its captive customer base.
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.
As far as I can tell these tools have quite a low ceiling. Great to start off with but but at some point I just find it easier to express myself with bezier curve handles than prompting. Canva, and Stitch (and maybe Claude Design) don't go that far.
Exactly, most SAAS tools out there are going to be fighting off AI based alternatives popping up or being integrated into general purpose tools. The people using the old tools will be switching to tools that offer them better productivity. For this particular tool, that means designers and frontend developers.
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.
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.
This seems a bit fiddly... I gave it the ChatGPT iframe html for my (not yet released) Liveclip MCP server that's like tables [https://x.com/firasd/status/2039926453408776649]. And I had this chat in the sidebar and it popped up some questions in a form
> 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.
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.
Will give it a try but my experience with Claude and browser use so far is that it’s extremely lazy: it rarely notices or cares when something doesn’t look right, it needs lots of pointing out “hey you ignored that broken render” etc
206 comments
[ 15.1 ms ] story [ 680 ms ] threadSeems 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?
I have been doing fine just instructing Claude code to use Tailwind and reference design documents
Go ahead and roast me.
I wonder what other features they're cooking right now.
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
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.
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 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.
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! :)
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)
Designs have been settling on a local maxima. If you are aware of a better hill to be climbed, please do let everyone know.
It’s 2026 and every web application has a different menu layout, date picker, etc.
p.s. Perhaps “quirky” is less because it’s simply not fulfilling? Too often it’s visual gaslighting pretending to be design?
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.
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
Very interesting though
- 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.
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.
You’re talking about art, not design.
I guess that kind of thinking got us liquid glass - which everyone hates.
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.
That link is redirecting me to https://claude.ai/404, anyone else?
Maybe AI is not good at everything, yet.
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.
This app is pretty slick, this will funnel a huge number of customers away from Figma + Canva imo.
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 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.
> 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 ...