Freelancers using Stitch.ai in London
Freelancers using Stitch.ai in London
Sign Up
Post a job
Sign Up
Log In
Filters
2
Projects
People
Neelanjana Basu
London, UK
AI builder with 10+ years in consumer product
$5k+
Earned
6
Followers
Follow
Message
AI builder with 10+ years in consumer product
1
Here’s my submission for the Google Stitch Challenge A vibe mapping product called Drift! It started with a small idea: what if a map could feel like the place it shows? What is it and what does it do? DRIFT turns every neighbourhood into its own visual identity. As a p0, starting with London. Camden is a punk zine. Chelsea is an oil painting. Soho is manga. Brixton pulses with Caribbean folk art. 93 neighbourhoods, 12+ art styles. All of these were derived from real Google Maps Platform data. The art style IS the information. APIs: Maps JavaScript API, Places API (New), Geocoding API. How I Built It? Every screen was built through Stitch’s streaming agent by describing what I wanted, watching it generate live, correcting through the agent. For all screens, I used variants to explore different art directions. DESIGN.md captured the emergent design system; I exported and re-imported it for consistency. I then prototyped in Play Mode, then exported to AI Studio and deployed on Cloud Run. Features used: Streaming Agent, Agent Manager, Variants, DESIGN.md Export/Import, Play Mode, Code Export. Stitch Feedback What I loved: Image quality is exceptional. I almost want to print and frame some the art it generated. Variants are absolutely essential for creative work and generating variants once saved me a lot of back and forth. The workspace itself is very smooth with low latency. Fantastic selection of export integrations available, with key platforms covered. What could be made better: Context doesn’t persist between screens (need a “project rules” feature). Undo wipes entire history, not just the last change. Chats are not threaded in the same way as other genAI chatbots, which took a bit of getting used to. Exports to build envirenments outside of AI Studio is restrictive (I tried Lovable as well and could only export 10 screens).
1
1
233
2
<Posting this for the second time because I mistakenly included the draft video in the first post> Hello! I am a big fan of Lovable, so couldn't let this challenge go by. For this brief I was inspired by my recent experience of booking after school clubs at my son's new school. It was full of friction and back and forth exchanges, and as annoyed I was with the process, I also felt for the service provider who is likely going through the same churn with every parent trying to book an after school club. So, for this demo I rebuilt the booking operations of a small local business called AfterBell Collective, which runs specialist clubs for 840 pupils at Hollybrook Primary School in London. It's owner Samantha used to juggle answering enqueries via phone and emails, manually confirming bookings, maintining waiting lists, chasing payments and reconciling received bank transfers by hand. And because bookings are made for one term at a time, she went through the same groundhog day thrice a year! I rebuilt the journey from enquiry to confirmed place so that one booking confirms the spot, manages conflicting schedules and updates payment, register and dismissal records at school at once. This saves Samantha up to 100 hours a term! This is also great for parents, who can now see suitable clubs, live availability, timetable clashes and the full term cost before booking. They can add siblings, apply the correct discount and combine a club with school-run wraparound care. For Samatha, one confirmed booking immediately updates AfterBell’s payment record, club register, capacity planning and the waiting list. The provider dashboard then handles payment reminders, private parent communications, absence checks, session information and cascading waitlist offers. Whilst it won't put her business on 100% auto-pilot, because real world complications will remain, but for most part she no longer has to hold everything together through her inbox. Using Lovable was a breeze! Loved the free chat functionality, which saved me a lot of Lovable credits (or braintorming tokens elsewhere). I also used the built in SEO and Agent integrations functionalities to make my website more discoverable to humans (and agents too apparently). I used Elevenlabs and Descript and Capcut to make the attached video, but would have loved if there was an inhouse functionality or connectors to popular video editing websites (Elevenlabs connector was super useful!) Overall, a very enjoyable process of building. Please check out the website leave some feedback for me!
2
165
4
STASH: Save. Build. Ship. A place where ideas roost, build, and take off. Say Caw Caw to KROWE, the mascot for STASH! It is the home for all the side projects you start and never quite finish; KROWE is the crow who gets them out the door. Character brief: KROWE is the non-conformist crow who runs STASH, the portal where side projects get saved, built, and shipped. It scavenges the half-finished ideas everyone else lets rot and tucks them somewhere they can actually come back to life. Sharp, resourceful, and quietly relentless, it turns 2am sparks into shipped reality. KROWE is the difference between an idea dying in a forgotten tab and an idea going live. Whatever you stash, KROWE helps you ship. Palette: ink #14110F · bone #ECE7DF · electric blue #2D6BFF · emerald #10B981 · volt amber #FFB81F Note on the craft: @recraftai The entire project was built in Recraft Studio with a saved Recraft style for character consistency, Vectorize for the logo, and Convert-to-mockup for merch. The same KROWE (locked palette, one silhouette, one volt-amber lightning beak) was carried across a logo, sticker pack, poster, merch, an app icon, a 6-frame story, and a 30-second motion piece. Here is the project link: https://www.recraft.ai/project/f01d58ff-17c9-4e99-b1aa-0b6b40da8b84 I am adding the video here and the rest of the assets in the comments.
4
4
780
28
Flat-pack furniture gives you two options: a baffling paper diagram, or a hunt that leads to long, confusing YouTube videos. Assembli solves that. It's an interactive 3D guide that shows you exactly what goes where, part by part. It is built for retailers, who lose $20-30 on every return, and 1 in 5 flat-pack returns is just someone who could not figure out the build. Assembli eliminates that confusion before it becomes a return or a support ticket. Made entirely in Omma, from one stool to a full catalog of 18 products. The video walks through it. PS: the link says "matte-black-sneaker-studio" because this began as a totally different idea before I pivoted to Assembli, and the slug got locked at first publish! Live build: https://omma.build/p/matte-black-sneaker-studio-shot-xn5evb (https://omma.build/p/matte-black-sneaker-studio-shot-xn5evb)Community file: https://omma.build/community/f6cfmk4ma6d9
8
28
1K
Stitch.ai
(1)
Follow
Message
Cătălin Dobrean
London, UK
I’m a dedicated Digital Product Designer based in Europe.
Follow
Message
I’m a dedicated Digital Product Designer based in Europe.
0
Brand & Client Management Tool - Design + AI
0
124
0
WeSupply SaaS - Product Design
0
6
2
AR/VR App & Identity Concept
2
24
1
Robotics Valley Branding
1
13
Stitch.ai
(1)
Follow
Message
Explore people
