An AI stylist that feels personal to every user
From browser beta to native iOS and Android apps, with a styling engine that learns.
A consumer AI fashion start upProblem statement
What the client was up against
A founder had validated an AI stylist in a closed beta and needed a downloadable, paid app that felt personal to every user, on a start up budget.
Our approach
How we approached it
- Audited and kept the existing stylist engine
- Built one Flutter codebase for iOS and Android
- Added a daily outfit loop using wardrobe, weather and plans
- Built a feedback loop so recommendations improve
Solution we created
What we built
Native apps with onboarding, wardrobe capture, avatar try on, an Ask Stylist journey, subscriptions and analytics, on a secure Node.js and Supabase foundation.
Agents in the system
The multi agent team behind it
SourcesSupabase, Node.js, Stripe, Apple and Google stores, weather data
Stylist engineBuilds outfits from wardrobe and context
Rules pipelineApplies style rules consistently
Ranking agentPersonalises from likes and swaps
People decideReview, approve and act
Stylist engineBuilds outfits from wardrobe and context
Rules pipelineApplies style rules consistently
Ranking agentPersonalises from likes and swaps
SupabaseNode.jsStripeApple and Google storesweather data
What it was built to change
The outcome it is designed for
A first useful outfit in under two minutes and a launch foundation for at least 1,000 active users.
This is a pilot without published results yet. We show the problem and the build, not numbers we have not measured.
Client names, detailed case studies, demos and references can be shared on request.
Looking for a similar solution?
Tell us your version of this problem. We will walk you through what we built and what a first pilot would look like for you.
