Skip to content

jasminepoon/figma_make

Repository files navigation

Taste Score

An intent configuration interface. Language in, readable trait score out, artifact updates live.


The Thesis

When you prompt an AI — "formal and warm," "minimal but expressive" — the interpretation is invisible. You can't inspect it, tune it, or carry it forward. This prototype makes that interpretation explicit: a five-axis radar you can edit directly, before generation runs.

The chain: prompt language → extracted traits → radar edits → artifact mutation


What It Does

You enter natural language preferences. The model extracts them into a trait score — discrete axes with values between 0 and 1, each mapped to CSS variables. Drag a point on the radar and the profile card updates live. Export a soul.md — a portable, machine-readable spec of your taste.

When two traits share a CSS variable, conflict resolution is typed: numeric properties blend proportionally, colors mix per channel, categorical properties (font family, easing) go to whichever trait has the strongest opinion — with hysteresis to prevent jitter on near-ties.


Running Locally

Requires Node.js. No install step.

  1. Create a .env file in the project root:

    OPENAI_API_KEY=your-key-here
    
  2. Start the server:

    node server.mjs
  3. Open http://127.0.0.1:4173

If port 4173 is taken: PORT=4174 node server.mjs


Stack

Vanilla JS + CSS — Node.js HTTP server — OpenAI Responses API (gpt-5-nano by default, swap via OPENAI_MODEL env var)


Docs

See agent_docs/ for spec, contributor guide, QA runbook, and acceptance criteria.

About

Intent configuration interface — language in, readable trait score out, artifact updates live.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors