ModelTaste

Feed the same brief to different models and compare who has better UI taste

Problem

Developers wonder whether AI models have a recognizable design taste and which one to pick for frontend work, but comparing means manually re-pasting briefs, re-running generations, and eyeballing screenshots — costly and unstructured.

Solution

Paste a frontend brief; the tool runs multiple models in parallel, renders pages side by side, and archives results with tags for typography, color, layout, and interaction; publish shareable comparison sets.

Users

Designers using AI for UI, indie developers, model selection evaluators

MVP

Brief input and parallel multi-model calls; side-by-side screenshot rendering; dimension tagging and scoring; shareable comparison links; run history

Revenue

Per-run API billing (BYO key free, hosted key with small markup) or $9/mo Pro subscription

Why now

Multi-model comparison is becoming a selection necessity while taste evaluation is a gap; turning generations into comparable assets is a lightweight product an indie can validate fast