Moûsa
Guessed22 Measured714
Qloo Agentic Hackathon · 2026

An entry to the Qloo Agentic Hackathon, 2026

Design for an audience from what it actually loves.

Moûsa is a plugin for the design agents teams already use: Claude Code, Codex and Kiro.

Your agent thinks it knows the crowd. It named 22 of 714.

Pick your seat. Read the source
Live facts

11 recorded sessions22 of 714 measured works named692 missing (96.9%)20 audiences, three agents60 sealed predictionsat most 24 requests a sessionanswers cached for a week55 open-licence font familiesmore than 500 tests

A lone microphone stand under one spotlight in front of a curtain

The problem

Tonight we roast the guess.

An AI agent asked to design for an audience designs from its own idea of that audience.

That idea is never tested.

So the design looks plausible.

And generic.

Nice guess. Now check the scoreboard.

In 11 recorded Moûsa sessions in Claude Code, Codex and Kiro, the agents' sealed guesses named 22 of the 714 works Qloo measured for their audiences.

Guessed and measured 22
Measured 714
Missing from the guesses 692 96.9%

Around the league A pre-registered benchmark of 20 audiences. Share of the measured works each agent's sealed guesses named:

  • Claude Code6.8%
  • Kiro6.6%
  • Codex4.7%

Five innings. One method.

How it works, read left to right like the board.

  1. 1st

    Plan

    Moûsa picks the taste questions for the medium: which Qloo domains to measure (films, music, books, TV, brands, places, games) and which tags.

  2. 2nd

    Freeze the guess

    Before any Qloo data, the agent writes its own prediction of what the audience loves, and the design it would make from that alone. It is frozen and sealed with its SHA-256.

  3. 3rd

    Measure

    Moûsa asks Qloo what the audience loves in each domain, which style and aesthetic tags it carries, and which qualities its measured works share. At most 24 requests a session, answers cached for a week.

  4. 4th

    Design from the difference

    The agent writes a Design DNA: concrete devices for palette, type, motion, illustration and voice, each anchored to what Qloo measured. The surprises must move it away from the frozen sketch. Moûsa checks every device in the project's own design system (CSS custom properties, token files or a Tailwind theme), and the agent reviews screenshots of what it built.

  5. 5th

    Report

    The Taste Provenance report sets the guess beside the measurement, marks each measured name as new or predicted, and follows it to each device and to the screenshots reviewed.

The box score. Fine print included.

Every kind of evidence, and what each one does not show.

692of 714

The blind spot

In 11 sessions, 692 of 714 measured works were not in the guesses, and 22 of the 245 works the agents guessed were measured.

It does not show that the design is better.

60sealed predictions

The benchmark

Twenty audiences and three agents: Claude Code, Codex and Kiro. The protocol and all 60 sealed predictions were committed to the public repository before Qloo measured any audience. The guesses named 6.8% (Claude Code), 6.6% (Kiro) and 4.7% (Codex) of the works Qloo measured, and 14% to 16% of the works they guessed were among those measured. Both pre-registered hypotheses held for every agent. The agents knew music and TV best (about 10%) and films, brands and books least (2% to 6%).

It measures what the agents assume, not whether a design is better.

0.530.570.580.60

The mechanism

Four recorded pairs were each built twice from one frozen guess, once with Qloo's measurement and once from the guess alone. The distances between the two designs were 0.53, 0.57, 0.58 and 0.60, on a heuristic scale from 0 (alike) to 1 (unrelated). Every device of each Qloo design rests on a name the guess missed.

That scale is not a quality score.

p = 0.005each

Beyond the model's own variance

In repeated pairs of one website brief (12 generations), the blind sketches of both arms were alike (p = 0.81). After Qloo, the typography, structure, palette and overall distance separated (exact permutation test, p = 0.005 each). For game characters, the finished characters separated (p = 0.0079) and the blind sketches did not.

It shows difference, not preference.

A or Byou pick

The blind vote

Visitors see both designs of a pair without knowing which used Qloo, and choose the one the audience would rather have.

Voters choose themselves, and there are few.

Three agents. One engine.

Claude Code

/plugin marketplace add tritonsan/mousa then /plugin install mousa@mousa

Comparisons run as two subagents at once.

Codex

codex plugin marketplace add tritonsan/mousa then codex plugin add mousa@mousa

Codex's own image tool can paint the pictures a plan asks for.

Kiro

kiro-cli powers install plugins/kiro from a clone of the repository

Each person uses their own Qloo API key, entered on a local page, never in the chat.

Pick your seat.

Three ways in, all on the live site.

The live try Runs Moûsa in Kiro on the hosted server for an audience you name. Step one under a minute: Kiro's sealed guess beside Qloo's measurement Step two about five to ten minutes: builds both designs Access code in the submission's testing instructions The gallery Recorded sessions from all three agents. Each shows the design, its record and how to run it again The blind vote Which design would the audience rather have? You see both designs of a pair, not which used Qloo

The tour rider.

How it is built, and what it needs on the road.

  • One MCP server in Node 22, with no dependencies, packaged for Claude Code, Codex and Kiro from one source.
  • Four skills (taste-brief, design, compare, connect), 13 tools and 55 open-licence font families.
  • A write gate holds a design's files until its Design DNA is valid, in Claude Code and Codex.
  • Captures in a headless Chromium that can reach only the page it captures.
  • More than 500 tests, with no network or model call, run on Ubuntu and Windows.
  • The hosted site runs on one AWS CloudFormation stack: an instance behind CloudFront, with the keys in Secrets Manager.

Qloo's data stays put

Qloo's answers stay on the machine that asked for them.

The site and the public repository show the names Qloo measured, never Qloo's ids, scores or descriptions.

About this broadcast

This page was designed by Moûsa in Claude Code, twice, from one sealed guess: once with what Qloo measured about its audience, and once from the guess alone.

Its audience is described to Qloo as people who love This Week in Startups, The Original Kings of Comedy, the Los Angeles Dodgers, Chelsea F.C. and Live Nation: works and names the hackathon's judges are known for.

That description tells Qloo who the audience is. It is not a claim about any judge's own taste, and no judge endorses this entry.