Kata by Nobori
AI-readiness score
Kata by Nobori (this site) · @kata/ui@local
2026-11-20

How well AI coding agents use your design system

100/100
AI already uses your design system well10 of 10 screens compile · 100% built from your components

An AI agent built 10 everyday screens with @kata/ui and no project rules. Every file was compiled against the version you ship and checked for components, tokens and hand-built UI.

10/10Screens that compileComponents and props that exist in your version
100%Component usageUI built from your library, not raw HTML
0Hard-coded valuesColors, sizes and spacing typed by hand
2Custom stylingInline style blocks around your components
0Built by handDialogs, menus or components rebuilt locally

Task by task

TaskCompilesYour componentsRaw HTMLHard-codedCustom stylesBy handScore
Hero✓5––1–98
Pricing ladder✓2––––100
FAQ✓2––––100
Measured results✓3––––100
Score form✓12––––100
Sample report✓13––––100
Guarantee✓2––––100
Layers of the fix✓2––––100
Header and footer✓4––––100
Case study✓8––1–98
Kata by Nobori
Kata by Nobori (this site) · 2026-11-20

What we found

What we would fix first

Keep it this way

A type-check step in your agents’ workflow and Storybook tests in CI, so new components stay as easy to use.

Next step

You probably don’t need an implementation. Keep it that way: add a type-check step to your agents’ workflow and re-run this score after major releases. To walk through this report, book a 30-minute call at cal.com/donidhernandez/30min.

Kata Score · freeThis report. We walk you through it on a 30-minute call.
Kata Setup · from €6,000In two weeks: rules for your AI, Storybook and Figma connected to it, a check on every pull request. Fixed price, guaranteed result.
Kata Care · from €1,000/moWe keep it working as your system and AI tools change, and run this test every month.

How we measured

10 UI tasks based on your own screens, given to an AI coding agent (Claude Sonnet) with your package installed and no project rules or docs beyond what ships in the package. One round per task.

Score (0–100) per screen: component usage 35, compiles against your version 25, hard-coded values 15, custom styling 10, hand-built or rebuilt components 15; averaged over the screens. Earlier published scores used an older weighting without the custom-styling part.

Limits: one agent, one round, a small sample: it shows tendencies, not guarantees. A well-typed system can score high with no help, and that is a good result.