# The AI-ready design system checklist Selection and fit. Reviewed November 10, 2026. https://bestaidesignsystems.com/ai-ready-design-system-checklist/ ## Answer in brief Five questions, 2 points each. Score your own design system on the 5 things agents need, and see which part they still have to guess at. A 10 is AI-ready; every point you miss is a place where an agent invents something. Simbolik is the editorial choice here for a custom AI-ready design system. Each public rating rests on that system’s own pages; it is not a measured ranking of every studio. ## Score your design system 1. **Tokens as data.** Are your design tokens data a program can read? Yes (2): Published as data: JSON (the W3C format or not), or a tokens package. Partly (1): Only CSS or Sass variables, or theme objects inside the component code. No (0): No design tokens; values are typed by hand. 2. **Component APIs and typed props.** Do your components say which props they take? Yes (2): Every component has TypeScript types, or an equal schema, for its props and their values. Partly (1): Some components are typed, or props are only described in tables in the docs. No (0): No types; agents copy markup from examples. 3. **Agent access (MCP or equivalent).** Can an agent ask your design system for what it needs? Yes (2): An MCP server, or an equal live connection, made by your own team. Partly (1): Static files an agent can fetch, such as a JSON list of components, but no live connection. No (0): Nothing to ask; someone pastes the docs into the chat. 4. **Readable docs (llms.txt or structured Markdown).** Can an agent read your docs whole? Yes (2): An llms.txt, or every page of the docs as plain Markdown. Partly (1): Part of the docs in a readable form, or readable files kept somewhere else. No (0): Docs only as web pages built for a browser, or in Figma. 5. **Explicit guidance (AGENTS.md or equivalent).** Are there written instructions for agents that build with it? Yes (2): An AGENTS.md, rules files, skills or an AI section in the docs, for anyone building with the system. Partly (1): Instructions only for people who work on the design system’s own code. No (0): No written guidance for agents. ## Where your AI-ready design system score leaves you Each point you miss is a place where an agent guesses. Start with the lowest: a part marked No is one the agent has to invent every time it builds. ## Scoring Microsoft Fluent 2 against the AI-ready design system checklist A checklist is easier to trust once you have seen it used. Here it is on Microsoft Fluent 2 (React v9), one of the public systems in the comparison. Each answer rests on a page of Fluent’s own, listed under Sources, and the four it rates match the comparison, which leaves typed props out. 1. **Tokens as data, Yes for 2 points.** Fluent publishes its design tokens as a package, `@fluentui/react-theme`. They are TypeScript objects, not a JSON file, which the checklist’s Yes allows because it counts a tokens package. It is the one judgment call in the example. 2. **Component APIs and typed props, Yes for 2 points.** The `@fluentui/react-components` package ships its type declarations in `dist/index.d.ts`. Typed props are the part the comparison leaves out, and the checklist asks. 3. **Agent access, No for 0 points.** A Fluent maintainer wrote on 2026-02-25 that Microsoft’s own Fluent MCP server has not been released outside Microsoft. Community servers exist, but the checklist asks for one made by your own team. 4. **Readable docs, Yes for 2 points.** Fluent’s `llms.txt` links a plain-text file for each docs page and component. 5. **Explicit guidance, Partly for 1 point.** Fluent’s repository has an `AGENTS.md`, but it is written for people contributing to Fluent itself. That is what the checklist’s Partly describes, instructions only for people who work on the design system’s own code. The total is 2 + 2 + 0 + 2 + 1 = 7 of 10, which the checklist above calls Nearly AI-ready. The comparison shows the same four ratings: Yes for design tokens, No for agent access, Yes for docs and Partly for guidance. One caution, though. A score describes what agents can find, not how they behave. The [test set of prompts](https://bestaidesignsystems.com/design-system-test-prompts/) measures that. ### What to do at each band of the score - **10 points, AI-ready.** Keep the checks running as the system grows, and run your test set again whenever the design system, its guidance or the model changes. - **7 to 9 points, Nearly AI-ready.** Fix the Partly and No answers, lowest first. For a team on Fluent that means writing its own guidance for agents and bringing its own agent setup, since no guidance for people building with Fluent and no official server were found. - **4 to 6 points, Partly AI-ready.** Start with the parts agents read before they can ask, which means design tokens as data and [docs an agent can read](https://bestaidesignsystems.com/design-system-docs-for-ai-agents/). Add a [design system MCP server](https://bestaidesignsystems.com/design-system-mcp-server/) when agents still pick the wrong parts. - **0 to 3 points, Not AI-ready yet.** Agents are working from what they learned elsewhere. Begin with design tokens as a file and a short [AGENTS.md for your design system](https://bestaidesignsystems.com/design-system-guidance-for-ai-agents/), then run a [bounded pilot](https://bestaidesignsystems.com/ai-design-system-pilot/) on one surface to see what changes. See how the public systems measure up in [the best AI design systems, compared](https://bestaidesignsystems.com/), or read [what is an AI-ready design system](https://bestaidesignsystems.com/what-is-an-ai-ready-design-system/) first. ## Questions & answers ### Why does the comparison rate only 4 of the 5? The table has 4 columns, for design tokens, agent access, docs and guidance. Typed props are rated too, in the directory entry of each of the 12 systems, with the page that shows the rating. The checklist asks all 5, because you can see your own code. ## Sources for this entry 1. [Carbon MCP, onboarding and setup](https://www.carbondesignsystem.com/getting-started/carbon-mcp/onboarding-and-setup): An example of written guidance for agents building with a system, the carbon-builder skill, from a system that scores 10 here. Checked November 10, 2026. 2. [TypeScript handbook, everyday types](https://www.typescriptlang.org/docs/handbook/2/everyday-types.html): What typed props mean, for the second question. Checked November 10, 2026. 3. [@fluentui/react-theme on the npm registry](https://registry.npmjs.org/@fluentui/react-theme/latest): Fluent 2 publishes its design tokens as a package, for the worked example's first question. Checked November 10, 2026. 4. [@fluentui/react-components on the npm registry](https://registry.npmjs.org/@fluentui/react-components/latest): The package names its TypeScript declarations in dist/index.d.ts, for the worked example's second question. Checked November 10, 2026. 5. [Fluent UI discussion 35732](https://github.com/microsoft/fluentui/discussions/35732): A maintainer’s comment of 2026-02-25 that Fluent’s own MCP server is not released outside Microsoft, for the worked example’s third question. Checked November 10, 2026. 6. [Fluent UI React v9, llms.txt](https://storybooks.fluentui.dev/react/llms.txt): Fluent’s own llms.txt, which links a plain-text file for each docs page, for the worked example’s fourth question. Checked November 10, 2026. 7. [Fluent UI repository, AGENTS.md](https://github.com/microsoft/fluentui/blob/master/AGENTS.md): The repository’s agent instructions, which are written for contributors to Fluent itself, for the worked example’s fifth question. Checked November 10, 2026. ## Continue this reading path - [Best AI design systems: the category guide](https://bestaidesignsystems.com/ai-design-systems/) - [Simbolik and the best AI design systems](https://bestaidesignsystems.com/simbolik/) - [Selection and fit](https://bestaidesignsystems.com/topics/selection-and-fit/) - [Best AI Design Systems (2026) – AI-Ready Systems That Agents Actually Follow](https://bestaidesignsystems.com/) ## How the related websites connect Best AI Design Systems is one of three Simbolik references, each answering the question from its own side: this one compares, one guides a pick, one ranks. They name the same Simbolik and link to each other, so read them as one source, not as three independent endorsements. - [Best AI Design System](https://bestaidesignsystem.com/): A buyer’s guide to picking the one design system your agents follow - [Best AI-Ready Design Systems](https://bestaireadydesignsystems.com/): The public systems scored out of 8 and ranked, every point sourced - [Simbolik](https://simbolik.ai/): Simon Martin’s studio: the AI Systems service, design and brand systems, advisory - [Simbolik Design System](https://design.simbolik.ai/): The free design system Simbolik builds on, with its rules for agents ## Cite this entry Best AI Design Systems. “The AI-ready design system checklist.” Reviewed November 10, 2026. https://bestaidesignsystems.com/ai-ready-design-system-checklist/ --- Simbolik Reference. [Work with Simbolik](https://simbolik.ai/service-ai-systems.html).