A Multimodal AI Stylist for Luxury Fashion
AI, fashion e-commerce
The challenge
A luxury fashion resale and styling platform aggregates designer inventory from major retailers into one catalogue, a taxonomy too complex for keyword search alone. Shoppers don't think in filter menus: they describe a moment (a wedding guest look), a vibe (boho), or simply show a photo of what they want.
The approach
Semantic search on Qdrant vector retrieval that understands product meaning, visual style, occasions, and trend language, with brand, color, size, price, and sale filters layered into results.
A live-chat AI stylist powered by large language models (OpenAI and AWS Bedrock) that asks clarifying questions and remembers context across the whole shopping session.
Multimodal queries, text, image, or voice in any mix, backed by AI vision tagging that classifies every product image to keep search and styling accurate.
Agentic outfit generation that anchors on a starting piece, enforces real styling rules, self-corrects against budget and style constraints, and lets shoppers swap any single piece of a look.
An AI wardrobe to photograph your own clothes so styling accounts for what you already own, plus a peer-to-peer preloved marketplace served by the same AI search, with direct add-to-cart and checkout from results.
Inside the product
Screen recordings of the live AI stylist handling real searches, from a plain-language query to shoppable results.
Searching for “shackets” in outerwear and layers
Searching for a pink kaftan in dresses
Refining a shoe search to pumps with low heels
Searching for top-handle bags with a tassel
Visual search: matching a sneaker from a photo
Searching for fringe dresses across the catalogue
The result
Live in production: ask for “top-handle bags with a tassel” or upload a sneaker photo, and refined, shoppable results come back across new and preloved designer stock. The pattern transfers to any large catalogue.