3 days. 2 prompts. 1 wedding website.

Wanted to stress-test Claude Design on something I genuinely care about: 👰🏼‍♀️The website for my wedding in September. 10 years with my partner Agus, real deadline, real guests, no room for "AI template" energy.

Here's what I learned by day 3: Claude Design is not a standalone tool. It's a layer in a stack.

The actual workflow that worked for me: → Claude (chat) — drafted the brief, defined palette, structured the 13 sections before opening the canvas → Claude Design — executed in 2 prompts. All 13 sections. Live countdown, RSVP form, copy-to-clipboard buttons. The skeleton was real. → Claude (chat) again — debugged outputs, regenerated my CSS when I hit my weekly limit, planned the next surgical prompt → Claude Code (next) — will wire the RSVP form to Google Sheets

What surprised me: ✦ Reading my SVG monogram + brand brief and producing a coherent first pass ✦ The Tweaks panel — custom sliders that don't burn tokens ✦ How fast 70% of the structure appeared

Where it hit the wall: ✦ Burned my Pro daily allowance in 2 prompts. Inline comments cost credits too. ✦ The Tweaks panel generates a .jsx file that silently overrode my hand-edited CSS. Lost 20 minutes wondering why nothing changed. ✦ Some elements weren't selectable. Decorative star ornaments I wanted to delete? Couldn't click them. Had to spend a full chat prompt asking Claude to remove them. ✦ The output was structurally there but emotionally generic. The small details — animation timing, hover micro-interactions, the curated feel of a hand-crafted page — those still need a human and a tool like Framer.

🤔 The verdict: Claude Design replaces the blank page. It does NOT replace the designer's craft. It's an incredible preview-to-final-web step, not the destination.

For me, the real magic is the loop. Use Claude to plan. Claude Design to scaffold. Framer (or your tool of choice) to give it soul.

What's your stack? 👇

Such a transparent look at the 'loop'! As a Social Media Manager, I’m curious when Claude hit the wall on 'emotionally generic' elements, did you find that adjusting the prompt for high-fidelity micro-interactions was worth the token burn, or was it faster to just move the 'scaffold' into Framer for that curated feel?

Can Claude Design really replace designers, or does it simply prove why designers are still needed?

I'm building a web-based motion app for designers, and I already have a pretty clear idea of how the interface should work. But building every screen by hand at this stage would be slow and, honestly, unnecessary

Right now, I don't need perfection I need something visible enough to click through, adjust, and build from

And this is where Claude Design is actually useful! Not as a replacement for a designer (because let's be honest, the design itself is not the strongest part), but as a tool for quick UX sketches

I like experimenting with AI tools, and I often give them minimal direction on purpose, just to leave space for them to "think" a little on their own. And very often, that's exactly where these tools show how far they still are from being "designer killers"

At first glance, the interface can look pretty nice But then I enter the prototype with my curiosity, design thinking, and 9 years of experience, and the fairytale gets less magical

"Why did you add this?" "Because there was space"

"What does this button do?" "Nothing, I didn't think that far, sorry"

"What is this section for?" "Analysis of a *completely imaginary area we're not even working with in this product*

And that's the point! Claude Design can create a quick structure, but it doesn't truly understand the product, audience, logic, priorities, or tiny decisions that make an interface actually usable

So for me, it's a great tool for designers who already know what they're doing A fast executor for early UX A way to get a rough version out of your head

But definitely not a replacement for a designer ✦ btw, the video is a small peek into the product and the process behind the animation from my previous post

AI's great for scaffolding and prototyping different looks and layouts quickly, but still definitely needs a human touch. Animation looks great!