- Status
- Used in the sales workflow
- Stack
- React · TypeScript · Express · Gemini API · Playwright
- Evidence
- Working application and an end-to-end test suite. A walkthrough can cover architecture, generation flow, and failure handling.
Help clients see what they are buying.
A personalized AI lookbook that connects a fabric conversation to a visual buying experience.
At a glance
The problem
Fabric swatches do not help every prospect imagine a finished custom garment on themselves. That uncertainty makes a consultative sale harder.
My role
I selected the sales problem, designed the customer workflow, and built the application with AI coding tools. I owned integration, debugging, and verification.
Decisions that mattered
- 01Use a style profile and client photo to make the output personally relevant.
- 02Connect a React and TypeScript interface to an Express backend and the Gemini API.
- 03Treat generated imagery as a sales illustration; it is not a verified pattern, fit prediction, or manufacturing specification.
What changed
The lookbook became a primary tool in the clothing sales process. Clients could discuss concrete visual options instead of relying only on swatches.
What this establishes
The evidence supports real workflow use. No controlled conversion lift or exact revenue attribution is claimed.
What I would measure next
Measure time to a usable lookbook, generation failure rate, and consultation-to-order conversion.
Contact
Want a walkthrough of this work?