Generative AI Styling App
Visit curait.ai ↗GeminiSerpAPIVision ModelsStructured OutputsLLMsContext Refinement
A styling app that turns natural-language outfit intent into shoppable looks, with persistent style context across sessions and a TikTok-style feed for browsing outfits.
Problem
- Online shopping is organized vendor by vendor, but outfit intent is not.
- Users need broad search across stores, then compression based on occasion, formality, budget, body preferences, and taste history.
- Curait turns that open-ended search problem into shoppable outfits.
System design
The core challenge was hiding a 10-second multi-service pipeline behind a responsive feed.
Context Distillation
Onboarding and behavior compress into a short taste profile for each generation.
Parallelization
Search, ranking, and image generation run concurrently to avoid feed stalls.
Single-Pass Ranking
Numbered grids let the vision model rank options in one call.
Latency UX
Next outfits generate in the background and cached results are paced.
Tradeoffs
- Quality vs speed: longer model reasoning improves outfits, but hurts feed latency.
- Context vs friction: richer onboarding improves personalization, but delays the first useful result.
- General vs overfit: the profile has to capture taste without overreacting to one request or recent interaction.
- Perceived latency vs cost: pre-generating future outfits feels faster, but wastes compute when users stop swiping.