# preset AI Documentation

> Documentation for preset AI, the design system memory layer for AI coding tools.

## Pages

- [preset AI · Documentation](https://presetai.dev/docs/): Pick a path: scan a repo, set up enforcement, plug an AI tool in, or read about the memory layer.
- [reference] [Agent resources](https://presetai.dev/docs/agent-resources): Every surface AI tools can read: MCP server, llms.txt, per-page markdown, copy-to-AI.
- [guide] [Connect an AI coding tool](https://presetai.dev/docs/ai-coding-tools): One-line MCP install for each major AI coding tool. preset AI becomes the design-system runtime for the agent.
- [guide] [Claude Code with preset AI](https://presetai.dev/docs/ai-coding-tools/claude-code): Operating loop for Claude Code: read context first, generate with constraints, validate, propose canonical changes.
- [guide] [GitHub Copilot with preset AI](https://presetai.dev/docs/ai-coding-tools/copilot): Operating model for Copilot: gather context first, generate with intent-based constraints, validate, route canonical writes.
- [guide] [Cursor with preset AI](https://presetai.dev/docs/ai-coding-tools/cursor): Operating workflow for Cursor: discover context, generate within constraints, validate, govern canonical writes.
- [guide] [Windsurf with preset AI](https://presetai.dev/docs/ai-coding-tools/windsurf): Operating workflow for Windsurf: retrieve context, generate within constraints, validate, govern canonical writes.
- [guide] [Active guardrails](https://presetai.dev/docs/compliance/active-guardrails): Active guardrails combine pre-generation constraints, post-generation validation, and policy gates before apply: a controlled loop instead of ad-hoc assistant behavior.
- [guide] [Exceptions and escalation](https://presetai.dev/docs/compliance/exceptions-and-escalation): Three exception levels (local, domain, system), explicit escalation triggers, and review cadence. No permanent exceptions by default.
- [reference] [Rule model](https://presetai.dev/docs/compliance/rule-model): Rule shape, severity model, evaluation lifecycle, and quality criteria. The contract underneath every guardrail and validation check.
- [reference] [Validation and confidence](https://presetai.dev/docs/compliance/validation-and-confidence): Validation asks 
- [guide] [Set up enforcement](https://presetai.dev/docs/enforce): Install the MCP server and watch your first AI generation get redirected to a real preset.
- [guide] [Review what was extracted](https://presetai.dev/docs/extract): Confirm, edit, or reject extracted artifacts before they enter your memory layer.
- [guide] [First workflow](https://presetai.dev/docs/first-workflow): Connect a system, create one preset, validate it, and watch an AI tool generate against it. End-to-end in five steps.
- [guide] [Importing design systems](https://presetai.dev/docs/importing-design-systems): Connect a GitHub, GitLab, or zip source. preset AI extracts tokens and components into a reviewable preset.yaml.
- [concept] [Key concepts](https://presetai.dev/docs/key-concepts): Vocabulary for everything else in the docs: tokens, presets, patterns, drift, compliance modes.
- [concept] [Why the memory layer matters](https://presetai.dev/docs/memory-layer): Why longitudinal memory beats snapshot for design systems in the AI age.
- [guide] [CI integration](https://presetai.dev/docs/platform/ci-cd/ci-integration): Three ways to add preset AI to CI: GitHub Action (one-line), CLI for other systems, SARIF for security tools. Full configs for GitHub/GitLab/CircleCI/Jenkins.
- [guide] [Validate in PR](https://presetai.dev/docs/platform/ci-cd/validate-in-pr): Run drift + audit-copy + scan in PR; emit JSON/SARIF; block on configured severity. Rollout: Observe → Assist → Enforce.
- [reference] [Ingestion overview](https://presetai.dev/docs/platform/ingestion): External sources are inputs, not the long-term source of truth. Flow: external → normalization → canonical → governance + distribution.
- [guide] [Claude Code integration](https://presetai.dev/docs/platform/integrations/claude-code): CLAUDE.md snippet to attach preset AI MCP usage, plus installing the skill family (guidance skill, write-time hook, and slash utilities) materialized from your live design system. Validated end-to-end on inline hex, all-caps tracking, off-grid spacing, inline styles.
- [guide] [CodeRabbit integration](https://presetai.dev/docs/platform/integrations/coderabbit): CodeRabbit + preset AI MCP turns generic 
- [guide] [OpenAI Codex integration](https://presetai.dev/docs/platform/integrations/codex): AGENTS.md snippet to attach preset AI MCP. Works across Codex CLI, desktop, and IDE extension. Native enabled_tools/disabled_tools for review profile scoping.
- [guide] [Cursor integration](https://presetai.dev/docs/platform/integrations/cursor): Cursor Rule (.cursor/rules/preset.mdc) tells the agent when preset AI is the authoritative source. Validated on inline hex, all-caps tracking, off-grid spacing.
- [guide] [Figma integration](https://presetai.dev/docs/platform/integrations/figma): Connect a Figma file on /figma, choose which token types to sync (colors, spacing, radius), and use the drift panel to preview and selectively apply changes. preset AI never auto-overwrites. Figma proposes, you decide.
- [guide] [Figma MCP integration](https://presetai.dev/docs/platform/integrations/figma-mcp): Dual-server pattern. Figma MCP exposes the selection your designer is looking at. preset AI MCP exposes your tokens, presets, and rules. Together the agent generates code that respects both.
- [guide] [v0 by Vercel integration](https://presetai.dev/docs/platform/integrations/v0): Three-step workflow: define presets in preset AI, prototype in v0 (loaded as a registry), validate generated code with preset drift.
- [concept] [MCP](https://presetai.dev/docs/platform/mcp): MCP is the runtime that gets your tokens, presets, patterns, and constraints into Claude Code, Cursor, and other AI tools.
- [reference] [Confidence scores](https://presetai.dev/docs/product/health/confidence-scores): Confidence indicates how certain preset AI is about a token extraction. Compounds across 4 stages: detection, parsing, extraction, mapping.
- [reference] [Token analysis](https://presetai.dev/docs/product/health/token-analysis): Token analysis compares defined tokens (config files) vs actual usage (component code). Surfaces missing tokens, unused tokens, and component patterns.
- [reference] [Typography health audit](https://presetai.dev/docs/product/health/typography-audit): Six categories (foundations, tokens, semantic, responsive, accessibility, usage) score 0-100. Grade A, F. Common issues + fixes.
- [reference] [Content patterns](https://presetai.dev/docs/product/rules/content-patterns): Microcopy templates for error/empty/button/confirm/success patterns. Tone rules: helpful not blaming, specific not generic, plain language not jargon.
- [reference] [Feedback patterns](https://presetai.dev/docs/product/rules/feedback-patterns): Skeleton vs spinner rules, toast types and timing, contextual empty states, progress indicators, accessibility requirements.
- [reference] [Focus management patterns](https://presetai.dev/docs/product/rules/focus-patterns): Component-specific focus rules + keyboard navigation tables + WCAG requirements. Modals trap, menus wrap, combobox doesn\
- [reference] [Interaction states](https://presetai.dev/docs/product/rules/interaction-states): Consistent hover/focus/active/disabled states. Use focus-visible for buttons/cards, focus for inputs. Subtle transitions, complete disabled states.
- [reference] [Motion tokens](https://presetai.dev/docs/product/rules/motion-tokens): Four duration tokens (instant/quick/normal/slow), five easing tokens (out-quart/out-expo/in-quart/in-out-quart/linear). Semantic intent, not arbitrary numbers.
- [reference] [Responsive patterns](https://presetai.dev/docs/product/rules/responsive-patterns): Beyond hide/show. Six behavior types: layout-shift, variant-change, size-adaptation, content-truncation, component-swap, visibility. Mobile-first.
- [reference] [Transition patterns](https://presetai.dev/docs/product/rules/transition-patterns): Each transition conveys a specific spatial message. Pick by relationship: same thing morphs, peer content, hierarchy, overlay, in-place replace.
- [guide] [Color: setting up your system](https://presetai.dev/docs/product/studios/color): Four ways to start a color system, one staged review. Every candidate arrives named and scaled for light and dark; feeds to semantic roles are per-row opt-ins; contrast figures are measured, never estimated.
- [guide] [Icons Studio](https://presetai.dev/docs/product/studios/icons): Import icons from Phosphor/Lucide/Heroicons, define semantic roles (delete, save, edit), set size tokens, sync to MCP.
- [guide] [Typography Studio](https://presetai.dev/docs/product/studios/typography): Add fonts (Google/URL/upload/system), map families to semantic roles, set scale ratio and fluid sizing, preview in Article/Dashboard/Marketing contexts.
- [reference] [Workspace Home](https://presetai.dev/docs/product/workspace-home): Home answers three questions: where am I, what should I do next, is anything broken or disconnected?
- [guide] [Scan your repo](https://presetai.dev/docs/scan): Run the scanner on your codebase. Extract tokens, patterns, and candidate presets.
- [guide] [Snapshot a PDF](https://presetai.dev/docs/snapshot-pdf): Scan a brand-guidelines PDF to extract its declared tokens. Useful for agencies onboarding a client.
- [guide] [Snapshot a URL](https://presetai.dev/docs/snapshot-url): Scan a live URL to extract its computed design tokens. Useful when there is no codebase to scan.
- [guide] [Updating design systems](https://presetai.dev/docs/updating-design-systems): Re-scan a source you already imported; preset AI shows a diff of added, modified, and removed tokens before applying.