Comparisons run as two subagents at once.
/plugin marketplace add tritonsan/mousa
/plugin install mousa@mousaMoûsa · An entry to the Qloo Agentic Hackathon, 2026
Made to measure. Not off the rack.
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.
Guess first. Then measure. Then design from the difference.
Open the live site
or read the source, under the MIT licence.
The problem
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.
Blind spot
692 of 714
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. 692 of them (96.9%) were missing from the guesses.
A pre-registered benchmark of 20 audiences
The sealed guesses of three agents named this share of the works Qloo measured:
The programme
How it works, in five steps. Guess first. Then measure. Then design from the difference.
-
Step one
Plan.
Moûsa picks the taste questions for the medium: which Qloo domains to measure (films, music, books, TV, brands, places, games) and which tags.
Questions fit the medium.
-
Step two
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. The prediction is frozen and sealed with its SHA-256.
The guess is sealed before the tape comes out.
-
Step three
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.
-
Step four
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.
Surprises move the design.
-
Step five
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.
Guess beside measurement.
The evidence
Read the label. Every kind of evidence comes with its fine print: what it does not show.
Evidence Facts
Five kinds · each with what it does not show
The blind spot
692 of 714
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.
The benchmark
60 sealed
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.
The mechanism
0.53 · 0.57 · 0.58 · 0.60
Four recorded pairs were each built twice from one frozen guess, once with Qloo's measurement and once from the guess alone. These are the distances between the two designs, 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.
Beyond the model's own variance
p = 0.005
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.
The blind vote
Which one?
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.
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.
Three agents, one engine
Each person uses their own Qloo API key, entered on a local page, never in the chat.
Codex's own image tool can paint the pictures a plan asks for.
codex plugin marketplace add tritonsan/mousa
codex plugin add mousa@mousaFrom a clone of the repository.
kiro-cli powers install plugins/kiroYour turn
Name an audience. Watch the guess meet the measurement.
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.
The access code is in the submission's testing instructions.
Go to the live siteThe gallery
Recorded sessions from all three agents. Each shows the design, its record and how to run it again.
The blind vote
Asks which design the audience would rather have.
Ingredients
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 that 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.
About this page
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.