Fashion OS
An AI-powered personal wardrobe and styling system.
Problem
I had a wardrobe full of clothes but still struggled to decide what to wear. Most wardrobe apps treat clothing as inventory rather than understanding the person, their preferences and context.
Why I built it
It started as a genuine daily annoyance, and it turned out to be a good test bed for a much broader question: how do you build AI products around preferences that the user cannot fully articulate?
What I built
- 01
Wardrobe digitization, so a real closet becomes something a system can reason about.
- 02
Image understanding to describe garments in terms a styling decision can use.
- 03
A personal style profile that holds preference, not just category and colour.
- 04
Contextual outfit generation across occasion, weather and mood.
- 05
A feedback loop, so rejecting a suggestion teaches the system something durable.
Product screenshots
How do you get an AI system to understand something as subjective as personal style?
Product / AI decisions
The hard question is subjectivity: how do you get an AI system to understand something as personal as style? I treated taste as something to be learned from behaviour rather than declared in a settings screen, and designed the surface so every recommendation is easy to reject cheaply — because rejection is the highest quality signal available.
What I learned
Personalization only feels intelligent when the system is visibly willing to be wrong and adjust. Confidence without correction reads as a stranger telling you what to wear.
What I'd build next
Deeper context — calendar, travel and repetition-avoidance — plus a much lighter capture flow, since digitization is still the main cost of getting started.