Personalization · AI · Prototype
A homepage that plans itself
Three ways to build a shopper’s homepage, side by side: fixed, rule-based, and planned by an LLM, with a “why this?” on every module.
The problem
One homepage serves the reseller checking prices twice a day, the gift shopper and the vintage collector. Editorial picks work for the average visitor and miss almost everyone else.
Three modes
Switch between them in the prototype and the same shopper gets a different page.
- 1Fixed: the same layout for everyone, the control.
- 2Rule-based: category affinities choose the hero, carousels and price range, each labeled with why.
- 3LLM-planned: an LLM gets the shopper’s profile and a menu of modules and returns a layout with its reasoning. It handles odd mixes, like luxury goods and deal hunting, that rules get wrong.
Built with
An LLM API, live listings and five shopper personas, each designed to produce a clearly different page.