Had a fun weekend building Merisole ☀️ Designed with Google Stitch.

I'm a senior product designer working on e-commerce sites every day, so my real question going into this challenge was practical: how easily does Stitch slot into my actual workflow? Could I use it to spin up a polished, client-ready option in a single sitting or even take it all the way to a shippable site? To test that, I asked AI to create a fictional footwear brand, Merisole, and treated it like a real client project from brief to launch.

How Stitch fit into the workflow Before generating anything, I wrote a custom design.md. Type scale, color tokens, spacing rhythm, the editorial tone I wanted Merisole to carry and uploaded it into Stitch as a design system. That single step is what made the rest of the build feel coherent. Every screen Stitch streamed onto the canvas already spoke the brand's language, so I wasn't fighting drift between sections. This is exactly the part of my normal e-com workflow that usually eats hours! Getting AI tools to respect a brand spec was something that Stitch handled cleanly. By the way, the stream on canvas feature was one of the coolest interactions I've seen so far! It was like having a designer design on your screen remotely through AnyDesk!

From there I worked mostly through in-place AI edits: clicking a section, telling Stitch "to add it to another variation," or "add a hover animation on the cards," and getting changes in seconds. The streaming generations meant I was reacting to a real interface taking shape instead of waiting for a static result.

The motion work is where Stitch surprised me most. Native hover states, shader backgrounds, and scroll-linked animation. All authored inside the tool, no handoff to a separate motion app, no code wrestling. Then I exported the build out to Netlify in one step.

New features I leaned on

Custom design.md - design system applied across the whole project (kept every screen on-brand from the first generation)

Streaming generations to canvas (the whole first pass)

In-place AI edits via prompts + point-and-click (most of the polish phase)

Native motion, hover states, and shaders on HTML canvas

Netlify export (final deploy)

Feedback on the platform Coming at this from a daily e-com design seat: Stitch genuinely shortens the distance between brief and client-ready. The design.md - design system flow is the underrated hero, uploading a brand spec once and having Stitch honor it across every streamed generation is the closest I've felt to "AI that respects a brand." The streaming canvas is amazing to say the least! It collapses the "describe - wait - judge - re-prompt" loop into something closer to direct manipulation. In-place edits felt the most like real design work. I stopped writing long prompts and just pointed at things. Two things I'd love next: An option to tweak elements without having to prompt it. And a way to save in-place edit "recipes" so I can reapply a vibe across sections without re-describing it.

Stitch didn't feel like an AI tool I was wrangling. It felt like a canvas that happened to understand what I meant. Merisole came together in a single sitting because of that, and I'm walking away convinced Stitch has a real place in how I'll pitch and build e-commerce work going forward.

Check it out:

Live site (really fun to click around): https://merisole.netlify.app

Stitch project: https://stitch.withgoogle.com/projects/834230787052196219

Amazing!

SimpleRent - Contra Submission Post

Google Stitch Challenge Entry

PROJECT LINK

https://stitch.withgoogle.com/projects/14459373944360524996 WEBAPP LINK https://simple-rent-contra.vercel.app

PROJECT TITLE

SimpleRent - Student Rental Platform for Sri Lanka

Every year, university students in Sri Lanka leave their hometowns to study in Colombo. They arrive with no local knowledge and no housing plan. No platform was built specifically for them.

SimpleRent is a student-first rental interface that solves two linked problems in one product: find a safe rental near your campus or find a compatible roommate to share the cost.

Google Maps-centered property search, NIC verification flow, roommate board, landlord dashboard, multi-step onboarding, messaging interface, and more - entirely designed and iterated inside Google Stitch.

HOW I USED STITCH

Before generating a single screen, I designed my own logo - a map pin housing a rooftop icon - and imported it into Stitch to generate a design.md brand file. Stitch scanned the logo and produced a complete design system: color palette, typography, card radius, shadow depth, and spacing. Every screen inherited that system automatically from the start.

Each of the 18 screens was then streamed live to the canvas - letting me review and plan refinements on one screen while the next was still being generated.

Once screens were on the canvas, I used Stitch's in-place AI edit feature to refine specific elements without regenerating anything. I clicked directly on a footer, typed a prompt, and only the footer changed. Same for card layouts, button colors, and badge styling - precise, targeted iteration on exactly the element I chose.

For motion, I used Stitch's native HTML canvas to build the NIC verification animation: the ID card shakes first as a visual cue, then flips smoothly on double-click. Property cards lift and shadow on hover. Because Stitch renders native HTML by default, every animation played in real time directly on the canvas as I built it.

For the code pipeline, I used Stitch's MCP connection to import Antigravity. Antigravity handled the code-side refinements - the logic and structure that go beyond what a visual canvas touches. Stitch for design. Antigravity for code. A full design-to-code pipeline, linked through MCP.

FEEDBACK ON STITCH

The real-time streaming canvas changed how I design. You stop waiting for a result and start collaborating with it - refining the previous screen while the next one is still being generated. That shift alone made the process feel genuinely different from any other tool I have used.

The in-place edit feature removed the biggest frustration of AI design tools: the fear of regenerating something good just to fix something small. Clicking directly on an element and prompting only that element to change is the kind of control that makes iteration feel safe.

The MCP integration with Antigravity was the unexpected part. It bridges the gap between a design prototype and a real codebase in a way I did not expect from a design tool.

Stitch did not just speed up how I work. It improved the ideas I had while I was working.

This is the gold standard right here! Absolutely spectacular.