Freelancers using StitchFreelancers using Stitch
Cover image for Bayen AI โ€” an AI
Bayen AI โ€” an AI shopping agent, designed end-to-end with Google Stitch I'm launching Bayen AI before it's finished โ€” the realtime UX and agentic animations I built with Google Stitch were too fun not to share, and I'd rather show a real, in-progress build than a polished demo. The story. I found Stitch ~3 months ago and finally built the front end I'd been stuck on. I'm building Bayen solo โ€” infrastructure, backend, matching layer, all of it โ€” so the UI kept slipping. Stitch is what unblocked me. What Bayen is. An AI shopping agent: you prompt it, it matches and finds the right products across sources โ€” AliExpress, Amazon, Alibaba, and more โ€” so you can find, track, and buy in one place through the sources' official APIs. People first; businesses later. This is a product I'm actually shipping, not a challenge demo โ€” just an early phase. ๐Ÿ› ๏ธ What I built A complete, on-brand frontend, generated with Stitch during the challenge: Personalized home โ€” auto-matches to signals (location, currency/language, browsing) with a "matched for you" feed. The agent โ€” an animated prompt composer: Smart / Deep Smart modes, voice, camera (shop-by-photo), a multi-source toggle, and a / skill palette of source "portals" the agent can call โ€” aliexpress_portal, alibaba_portal, amazon_search, /compare, /track, /under. Realtime PDP โ€” live price + drop indicator, 30-day sparkline, USD/EUR/MAD switcher, and a Compare Offers table flagging the best live source. Payment handoff โ€” routes the buyer to the source's official checkout (e.g., Amazon) with affiliate disclosure, plus a Track price popup. Admin โ€” dashboard, orders, returns. Design: monochrome zinc + one confident red accent, Poppins (JetBrains Mono for prices), an animated lowercase bayen ai wordmark, full light/dark + responsive. ๐Ÿ”— Link https://stitch.withgoogle.com/projects/6579973469378019461 (https://stitch.withgoogle.com/projects/6579973469378019461)โœจ How I used Stitch Stitch generated my entire frontend, not just mockups โ€” via its 2026 Vibe Design workflow: Multi-screen generation โ€” I described each route in natural language; Stitch produced the whole connected flow (home, agent, PDP, payment, admin). Design system as text โ€” I fed it a structured spec (tokens, type ramp, components) in the spirit of Stitch's DESIGN.md format, so every screen stayed in the same zinc + red + Poppins language. Streaming design agent โ€” refining by prompt/voice with live render let me pivot the whole system (flat monochrome โ†’ Poppins + red, then rebuild the composer and admin sidebar) in minutes. Newly launched feature showcased: Vibe Design + multi-screen generation, plus the streaming design agent. ๐ŸŽž๏ธ Motion, interaction & dynamic UI Send โ†’ generation โ€” the prompt rises into a bubble, the agent streams its "thinking", the reply types in, then product cards stagger in with deal badges popping and prices counting up. Dynamic composer โ€” sliding Smart/Deep Smart toggle, source dropdown with a number-pop, voice waveform + timer, and a / palette that filters as you type. Realtime feel โ€” a Live Deal Tracker with pulsing "live" dots and price deltas, plus a price-confirming state in the payment handoff. ๐Ÿ”Œ External integrations (in progress) Headless: a Shopify backend for owned catalog/orders, and official source APIs (AliExpress, Amazon, Alibaba) for matching, live pricing, and the buy handoff โ€” with multi-currency FX. ๐Ÿ’ฌ My feedback on Stitch Loved: the speed (idea โ†’ real screens) that finally unblocked my front end; natural-language multi-screen generation that kept the flow coherent; design-system-as-text (DESIGN.md-style) that made a brand pivot ripple across every screen; real, buildable structure, not just pictures. Would love next: finer motion-timing/prototype-link control so animated states export as a playable flow; deterministic tokens (lock a hex/spacing scale); better real image fills and reusable components. Net: Stitch went from "fun to try" to the core of my workflow. ๐Ÿ–ผ๏ธ Screenshots / recording Agent match feed, PDP with Compare Offers, personalized home, Admin dashboard โ€” plus a recording of the animated prompt โ†’ results flow. ๐ŸŽฅ Walkthrough (bonus) Video attached, and on Loom (https://www.loom.com/share/85be2bf6a40c41c5aceca35ff8f44c01). Note: brand names (Amazon, AliExpress, Alibaba) are referenced as planned official-API integrations; product imagery is placeholder/generated.
2
290
Cover image for โœˆ๏ธ AI Travel App Concept
โœˆ๏ธ AI Travel App Concept for the Stitch Challenge For this Stitch Challenge, I decided to test what AI can do in my strongest zone - mobile app design. My agency and I have created 350+ mobile apps across AI, hospitality, wellness, hotel platforms, marketplaces, and travel-related products. So instead of creating just a nice UI shot, I wanted to test Stitch on something closer to a real product. The concept: An AI Trip Planner App that helps users discover trips, generate a personalized travel plan, optimize the budget, and turn everything into a ready itinerary.The main UX idea was to show how an AI travel agent can guide the user from curiosity to action: โ†’ Discover trip ideas โ†’ Generate a plan โ†’ Build a route โ†’ Optimize budget โ†’ Show savings โ†’ Push the user toward booking I used: a product specification a Claude-generated visual reference the same prompt direction in Stitch then Figma polishing to improve spacing, hierarchy, consistency, and final presentation Claude gave me a strong visual reference. Stitch gave me the first working structure. The biggest advantage of Stitch for me was iteration speed. With the free / Gemini access, I could generate and test more without constantly thinking about tokens. Claude is paid in my workflow, so for fast visual exploration Stitch was actually useful. After Stitch generated the first version, I refined it in Figma and turned it into a cleaner, more premium mobile concept. Final outcome: AI Travel mobile app concept Trip discovery experience AI trip planning flow Budget and savings logic Smart recommendations This challenge was not only about โ€œcan AI generate screens?โ€ ๐ŸŸขFor me, the real question was: Can AI help a senior mobile designer move faster from reference and prompt to a product idea that actually feels usable, structured, and business-focused? My answer: yes - but the depth still comes from UX strategy, product thinking, visual direction, and final design judgment. Live Link: https://stitch.withgoogle.com/preview/3633210786682110568?node-id=6fcf2b2aafa9411b8a6f7e377f220b81 If your mobile app looks good but users still donโ€™t activate, return, or convert - I can help you find the leak. Book a Mobile App Diagnostic Call: https://calendly.com/asol_design/book-diagnostic-call-linkedin-clone #stitchchallenge #stitch #mobileappdesign #uidesign #uxdesign #productdesign #aitravel #figma #growthdesign #mobileux
16
40
3.1K
Cover image for I'm jumping headfirst into this
I'm jumping headfirst into this challenge and sharing a project that will reimagine the health industry and showcase the full capabilities of Google Stitch. Everything that came out of this project exceeded all expectations. Nothing else could do what Stitch did. In this video, you'll see with your own eyes and fully realize that the time of AI has arrived. Big changes await us. Whoever is first to show this to the world will be the conductor of the future cyberpunk 2089. The project is called SomaOS Pulse. It's a wellness intelligence dashboard concept that integrates sleep, HRV, glucose, stress, activity, and nutrition signals into a single, vibrant interface. Stitch was used to generate the design system, screens, prototype, and animations, and then the project was polished into an interactive web prototype. I'm sharing my thoughts on the project. Follow the links: Google Stitch, prototype, interactive web version, my social media. Be sure to watch the video. Links Stitch prototype: https://stitch.withgoogle.com/preview/15691040717386817?node-id=f575de351f2d47719ea3f175cdbf726a Stitch: https://stitch.withgoogle.com/projects/15691040717386817 (https://stitch.withgoogle.com/projects/15691040717386817)Social Media X: https://x.com/den_turbin/status/2062278635923669285 Linkedin: https://www.linkedin.com/posts/denis-turbin_i-built-a-unified-live-ai-interface-that-ugcPost-7468044445842649090-QHnY/?utm_source=share&utm_medium=member_desktop&rcm=ACoAAEYVHPYB02O3S94UQCKAOJsgErYsJovzstc Threads: https://www.threads.com/@den_turbin/post/DZI1hm9kc5d Kisses and greetings to everyone. Let's cook this challenge!
4
8
482
Cover image for ASPHALT is a landing page
ASPHALT is a landing page for a street skateboard brand โ€” one long scroll with six sections: hero, the drop, the boards, the numbers, the culture, and a final call to action. Live: https://asphalt-skate-culture.netlify.app/ The look is raw and bold: paper background, big chunky type, yellow and orange accents, 3D boards in the space. Almost everything moves : a spinning skate-wheel cursor, text that jumps up on scroll, a board that tilts to your mouse, a trick-name ticker, a counting year, and sparks on the last button. How I used Stitch https://stitch.withgoogle.com/projects/768150956399471213 I started with a design system. I wrote a DESIGN.md with the colors, type scale, spacing, and motion rules, then imported that into Stitch as the source of truth. From there Stitch generated each section straight onto the canvas, and because everything ran off the same system, the sections actually matched instead of drifting. The output was HTML-native too, so the motion and hover states were already in there. Once the sections looked right, I exported the code and used Claude to merge them into one page: combining the duplicated cursor, consolidating the Tailwind config, and wiring up the scroll behavior between sections. Then I shipped it on Netlify. Platform feedback Starting from a design system was the best part the DESIGN.md kept all six sections consistent, which is usually the hard bit when you build piece by piece. Fast too, and the motion came baked in. The one pain point was joining sections. Each exports on its own, so making one page meant cleaning up duplicates by hand. A "merge boards into one page" export would fix that.
4
12
1.9K
Cover image for Project title
STALL โ€” Your farmers
Project title STALL โ€” Your farmers market, alive. A swipe-to-shop farmers market companion that connects local vendors with regulars before Saturday ever arrives. The problem Every Saturday, the same thing happens. You show up to the farmers market at 10am. The ramp vendor you wanted is sold out by 9. You forgot cash. You walk past a honey stall three times because you can't remember if you already bought some. And that new mushroom farm you heard about? Gone before you spotted them. On the vendor side, it's just as frustrating. Small farmers wake up at 4am, load the truck, drive an hour, and have no lightweight way to tell their regulars โ€” the people who actually want what they grow โ€” "I have asparagus this Saturday. Come find me." STALL fixes both sides of that problem. What STALL does STALL is a two-sided farmers market app built around one weekly ritual: Saturday morning. For shoppers: Follow vendors at your local market Swipe through a weekly produce deck โ€” right to add to your list, left to skip โ€” exactly like Bumble, but for ramps and sourdough Get a Friday evening digest: what your vendors have this week, your auto-built shopping list, and where each stall is on the map Pre-reserve high-demand seasonal items before you leave the house Discover first-of-season arrivals with a "what's new this week" spotlight For vendors: Post a weekly inventory update in 3 taps โ€” what you're bringing, quantities, price Reach your regulars directly before market day Manage pre-reservations without a complicated system The app celebrates the seasonal nature of farmers markets โ€” ramps in April, strawberries in June, squash in October. Every week feels like something worth showing up for. How I built this with Google Stitch STALL was designed and prototyped entirely using Google Stitch as the primary build tool, with Figma used only for initial wireframing. The workflow: Day 1 โ€” Brand and wireframes I started by defining the brand: the name, palette (Pumpkin Spice Forest โ€” a warm amber, fern green, mauve, and cream system), and illustration direction. I wireframed the three core flows โ€” swipe deck, Friday digest, and vendor post โ€” before touching Stitch. Day 2 โ€” Into Stitch I imported my Figma file directly into Stitch using the .fig import feature. From there I used streaming generation to build each screen live on the canvas โ€” watching the splash screen, onboarding flow, and homepage assemble in real time was genuinely remarkable. The HTML-native canvas meant every animation I added โ€” card tilt on swipe, drawer slide-up, bento tile stagger โ€” rendered exactly as it would in production. Key Stitch prompts used: "Add a swipe gesture to the produce card stack โ€” right swipe shows a green Added overlay with 5ยฐ card tilt, left swipe shows a mauve Skipped overlay with -5ยฐ tilt" "Make the shopping list items stream in one by one with 120ms stagger on page load" "Add a bottom drawer that slides up from the vendor card with spring easing โ€” show the farm bio, full inventory list, and two action buttons" "Build the Friday digest screen โ€” vendor items animate in sequentially, the seasonal spotlight card pulses gently" "Export web assets and deploy to Netlify" In-place edits I used: Swapped the swipe overlay color from red to mauve to match brand Adjusted the bento grid gap from 8px to 6px after seeing it render on canvas Changed the CTA button from outlined to filled after in-place visual comparison Rewrote the seasonal spotlight copy directly on the canvas without regenerating What Stitch made possible that nothing else could: The swipe gesture interaction, the drawer spring animation, and the staggered list streaming โ€” all three of these would have taken days to hand-code. In Stitch, they were prompt-driven and live on the canvas within minutes. The gap between "designed" and "interactive prototype" collapsed entirely. Screens delivered Splash screen โ€” farmer illustration, full-bleed cream background Onboarding screen 1 โ€” market basket illustration, "Your market, every Saturday" Onboarding screen 2 โ€” swipe mechanic explainer with card UI Onboarding screen 3 โ€” Friday digest bento preview Homepage โ€” bento grid with market header, seasonal spotlight, list, map preview, swipe deck, streak tracker Swipe deck โ€” card front, vendor expand drawer, swipe right (added), swipe left (skipped) Friday digest โ€” streaming vendor list, seasonal spotlight, auto-built shopping list Market day map โ€” vendor stall grid, spot numbers, live confirmation states Vendor post flow โ€” 3-tap inventory update screen Design decisions worth noting The swipe mechanic โ€” Borrowing the Bumble swipe pattern for produce discovery was the conceptual breakthrough. It transforms a passive browse into an active, satisfying decision. Every right swipe builds your list. Every left swipe still shows you where the vendor is on the market map โ€” skipping is never permanent. The Friday digest as the hero feature โ€” Most apps make you come to them. The Friday evening push notification with a personalised market brief is the one moment where STALL comes to you. It changes Saturday morning from reactive to intentional. Bento homepage โ€” Instead of a scrolling feed, the homepage gives you everything at a glance: your market, your list, the seasonal moment, your vendors. Seven tiles, seven pieces of information, zero scrolling. The color system โ€” Pumpkin (#E8872A), Fern (#728040), Mauve (#B07090), Cream (#FDFAF6), and Moss (#4A5228). Every color has one job. Pumpkin is interactive. Fern is seasonal and confirmed. Mauve is reserved and streaks. Cream is every surface. Nothing competes. What I learned Stitch genuinely changes the prototyping workflow. The moment I stopped thinking of it as a design tool and started thinking of it as a build tool โ€” one where the canvas is the product, not a picture of the product โ€” everything accelerated. The in-place edit feature is the one I'll keep coming back to: being able to change a color, rewrite copy, or swap a component without regenerating the whole screen is the difference between iteration and rework. STALL started as a hackathon idea. After building it in Stitch, it feels like something real. Live Prototype: https://stitch.withgoogle.com/preview/8229547464152593644?node-id=e53124995cda49808685283be978dc8c
50
44
1.1K
Cover image for Most travel apps solve booking.
Most travel apps solve booking. None of them solve the reason people never book in the first place. The problem is not money. Most people who want to travel actually have enough. The problem is that travel has no due date. Your EMI comes out on the 5th. Your insurance renews in March. Your electricity bill arrives every month without asking. They all get paid - because they have a structure that does not accept someday as an answer. Your dream trip has none of that structure. So it waits. Every year. Until it stops feeling like a plan and starts feeling like a personality trait. That insight became Voya. This is the Original Workflow (https://stitch.withgoogle.com/projects/6972276730042508148) but due to certain issues I am not able to create prototype in same file so I duplicate that workflow (https://stitch.withgoogle.com/projects/17661579163113846531) and create new prototype. Prototype: https://stitch.withgoogle.com/preview/17661579163113846531?node-id=052829c9edd64f84b05c85db6b5bd998 ๐—ช๐—ต๐—ฎ๐˜ ๐—บ๐—ฎ๐—ธ๐—ฒ๐˜€ ๐—ถ๐˜ ๐—ฑ๐—ถ๐—ณ๐—ณ๐—ฒ๐—ฟ๐—ฒ๐—ป๐˜: โ†’ Saves a fixed amount from your income every month automatically - like an EMI, but for your next trip โ†’ Shows you where your rupee goes furthest right now based on live currency exchange advantages โ†’ Monitors flight prices 24/7 and alerts you the moment fares drop on your target routes โ†’ Tracks hotel pricing cycles so you book the same property for significantly less โ†’ Forecasts exactly where you can travel with your current savings - and when you unlock better destinations in 3, 6, or 12 months โ†’ Builds four completely different trip packages for the same destination - one for people who want luxury hotels and economy flights, one for business class comfort with simple stays, one for slow deep travel, one for multi-city discovery - you compare and pick yours โ†’ Shows you the real cost of waiting - how much more you will pay if you book when you originally planned versus booking now with your savings โ†’ Gives you back the mental peace of knowing the trip is already funded - so when you return home you return to the exact financial life you left. No investments liquidated. No recovery period.
67
46
1.5K
Cover image for Iโ€™m happy to take part
Iโ€™m happy to take part in this challenge and share my project created with Google Stitch โค๏ธโ€๐Ÿ”ฅ For this challenge, I designed a marketing landing page for a sleep improvement app that helps users build better sleep habits ๐Ÿ˜ด [๐—ช๐—ผ๐—ฟ๐—ธ๐—ณ๐—น๐—ผ๐˜„]I used Google Stitch throughout the whole design process: - Imported my design system from Figma - Added visual references - Generated the first version of the interface with prompts - Improved the content and layouts using AI edits - Added animations and interactions to complete the experience [๐—ž๐—ฒ๐˜† ๐—ฆ๐˜๐—ถ๐˜๐—ฐ๐—ต ๐—™๐—ฒ๐—ฎ๐˜๐˜‚๐—ฟ๐—ฒ๐˜€ ๐—จ๐˜€๐—ฒ๐—ฑ] In this project, I explored several Stitch features: - Design imports - AI editing - Prompt-based UI generation - Animations and motion ๐—˜๐˜…๐—ฝ๐—ฒ๐—ฟ๐—ถ๐—ฒ๐—ป๐—ฐ๐—ฒ ๐Ÿคฉ I really enjoyed working with Stitch. The workflow felt intuitive and easy to understand, making it simple to move from ideas to polished screens. Creating and updating layouts was fast, and the AI-powered editing significantly accelerated the design process. I also appreciated how seamlessly Stitch worked with my existing design assets, allowing me to combine my design system with AI-generated concepts and iterate efficiently ๐—Ÿ๐—ถ๐—ป๐—ธ๐˜€ Prototype: https://stitch.withgoogle.com/preview/14073781857777698748?node-id=10b283821f014ccab41648d62b15bf7e&raw=1 Project File: https://stitch.withgoogle.com/projects/14073781857777698748 Workflow Video (the same video as the one attached) : https://drive.google.com/file/d/1y1NIdNjLn1JM2S_s2wYpn0jR1nB-nyoj/view?usp=sharing ๐Ÿ˜‡ ๐—ฆ๐˜‚๐—ฝ๐—ฝ๐—ผ๐—ฟ๐˜ ๐— ๐˜† ๐—ฆ๐˜‚๐—ฏ๐—บ๐—ถ๐˜€๐˜€๐—ถ๐—ผ๐—ป ๐Ÿ˜‡ If you enjoyed this project and found the workflow demonstration valuable, I would greatly appreciate your support. Thank you for taking the time to review my submission โค๏ธ
111
155
9.1K
Cover image for Transform Ideas into Digital Worlds with AFTERCUBE AI Studio
AFTERCUBE โ€” AI Visual Worlds From Raw Ideas For the Google Stitch Challenge, I created AFTERCUBE โ€” a dark cinematic AI visual studio that turns raw ideas into website concepts, brand systems, motion direction, and immersive digital worlds. The idea was simple: What if one rough prompt could become a complete visual direction? Not just a layout. Not just a dashboard. A full world. AFTERCUBE is designed as a premium creative engine where users can start with a raw idea and generate cinematic website concepts, visual identity direction, interface systems, brand atmospheres, featured world concepts, and motion-ready digital experiences. The final landing page tells a clear story: Raw idea โ†’ visual engine โ†’ generated worlds โ†’ start creating Process I spent around [add hours here] hours exploring, designing, breaking, rebuilding, and refining this concept. This was not a one-shot design. I went through 20+ iterations before finding the final direction. Some early versions felt too much like generic SaaS dashboards. Some sections looked like separate websites instead of one continuous experience. A few visual directions were too cluttered, too flat, or not premium enough. So I kept stripping things back and rebuilding around one stronger visual language: dark cinematic background burnt-orange energy oversized editorial typography 3D character and engine visuals subtle grid texture premium Framer-style spacing animated interactions strong section rhythm The biggest challenge was keeping the page consistent while moving from hero to product explanation to showcase sections. I wanted the whole page to feel like one visual world, not random screens stitched together. How I used Stitch I used Stitch to rapidly explore different layouts, test visual directions, refine the brand system, and push the final landing page into a more polished prototype direction. The workflow included: Exploring multiple concepts and brand names Testing different dark visual systems Locking the final direction around AFTERCUBE Building the cinematic hero section Creating the Visual Engine section Adding Featured Worlds as generated concept examples Creating a final prompt-driven CTA Adding motion ideas, hover states, glow interactions, and scroll animation direction What I focused on My goal was not to create another generic AI landing page. I focused on: strong first impression cinematic art direction bold typography premium dark UI orange energy system clear product storytelling interactive motion visual consistency a page that feels like a real creative AI product Future direction If I had more time, I would expand AFTERCUBE into a deeper product prototype with: a full AI generation flow additional inner product pages more generated world examples more custom 3D elements animated world-building states a detailed brand system page export screens for Framer, Figma, and campaign assets interactive prompt-to-world transitions This version focuses on the core brand, landing page, and product story first. The next step would be turning it into a fuller interactive product experience. Feedback on Stitch Stitch was useful for fast ideation and visual exploration. It helped me test multiple directions quickly and move from rough concept to polished landing page much faster than starting from a blank canvas. The hardest part was maintaining consistency across sections. Some outputs looked like separate pages, so I had to keep refining prompts around continuity, layout rhythm, spacing, and brand discipline. Overall, Stitch was powerful for exploration, but the best results came from treating it like a creative partner โ€” testing, correcting, refining, and pushing the design direction intentionally. Final concept AFTERCUBE is an AI visual studio for turning rough creative thoughts into cinematic digital worlds. One prompt. One engine. A complete visual world. Prototype: https://stitch.withgoogle.com/preview/2647123046716225432?node-id=7b022a8e6ba245dd9a77627c3cc9e5ee
40
67
5.1K