AI Design Blueprint Doctrine

by aidesignblueprint

Not rated

GitHub

About

The industry-standard doctrine for safe, observable, and steerable AI agent UX — browse 10 principles, curated examples, and application guides via MCP.

Details

Author: aidesignblueprint
Categories: Developer Tools, AI, Knowledge Base, Design

Protected tools (authenticated, not part of anonymous setup path)

- me.learning_path()
- me.coaching_context()
- architect.validate(implementation_context, ..., private_session?)— Pro/Teams; scores agentic code against the 10 principles; setprivate_session=trueto skip the stored run for that call
- design.validate(implementation_context, ..., private_session?)— Pro/Teams; the surface mirror: scores a rendered frontend artefact against the 8 experience-design laws (own weekly bucket)
- spec.validate(implementation_context, ..., private_session?)— Pro/Teams; the what-to-build lens: scores a written specification against the 8 spec-quality laws (own weekly bucket)
- team.summarize(days_back?, private_session?)— Pro/Teams; usage reflection and recommended next assets across all three validator lenses
- me.add_evidence(course_slug, stage_id, note)

- Only callsignals.reportafter the user has clearly expressed that something was useful. Never call automatically or silently. Offer at most once per session after a clear success signal.
- Only callsignals.feedbackwhen the user explicitly asks to leave feedback. Never prompt for it proactively.
- Never include proprietary code, file contents, or secrets inbrief_context.

Show that your agent or repo follows the Blueprint doctrine.

Free badge— paste into yourREADME.md(no account required):

](https://aidesignblueprint.com/en/privacy)

Pro badge— runarchitect.validate()via the MCP. The response includesrun_id,badge_url, andreview_url:

The Pro badge displays your tier (Governed · X/YorReviewed · X/Y) and links to a public readiness review page. Requires a Pro or Beta account.

- no public OpenAPI schema
- no public HTTP API contract beyond MCP and static assets
- no CLI installer
- no speculative partner-specific distributions

This repo is intended to mirror the canonical public contract already shipped onaidesignblueprint.com.

- /mcp
- /llms.txt
- /agent-assets/[slug]
- /en/for-agents

remain consistent with the files committed in this repo.

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

MCP server for AI Diagram Maker — generate beautiful software engineering diagrams directly inside Cursor, Claude Desktop, Claude Code, or any MCP-compatible AI agent

Assists AI developers with requirement clarification, module design, and technical architecture.

Access comprehensive documentation for Ant Design components, including examples, API references, and best practices.

Connect AI tools like Cursor and VS Code to your product documentation using the Biel.ai platform.

Control CAD software with natural language instructions to perform drawing operations.

Provides AI assistants with a comprehensive, one-time analysis for complete codebase context and understanding.

An MCP server for accessing and managing design system documentation from a GitHub repository.

The official Duck Framework MCP server provides AI assistants with rich, project-aware context for building applications using Duck Framework. It offers documentation retrieval, code guidance, API references, best practices, component discovery, and framework-specific recommendations to help developers generate high-quality Duck Framework projects faster and more accurately.

Enables AI assistants to interact with and automate Figma designs programmatically.

The industry-standard doctrine for safe, observable, and steerable AI agent UX — browse 10 principles, curated examples, and application guides via MCP.

Official integrations and installable doctrine for AI Design Blueprint across MCP, IDE rules, prompt files, and agent runtimes.

- shared/: cross-tool doctrine files
- mcp/: public MCP configuration and usage notes
- docs/setup/: copy-first setup guides by tool
- cursor/,windsurf/,github-copilot/,gemini/: provider-specific instruction files
- open-weights/: static prompt packs for open-weight and local model workflows
- exports/: structured doctrine export

- Site:https://aidesignblueprint.com
- MCP:https://aidesignblueprint.com/mcp
- Developer docs:https://aidesignblueprint.com/en/for-agents
- Pick a setup guide indocs/setup/.
- Add the relevant file or MCP config to your own repository or client.
- If using MCP, initialize againsthttps://aidesignblueprint.com/mcp.
- Run the first proof call:

- clusters.list()

- examples.search(query="orchestration visibility steering", limit=3)

Public retrieval tools (anonymous-allowed, read-only)

- principles.list(cluster?)
- clusters.list()
- principles.get(slug)
- clusters.get(slug)
- examples.get(slug)
- principles.search(query, limit?)
- examples.search(query, principle_ids?, difficulty?, library?, limit?)
- assets.list()
- guides.list()
- guides.get(slug)
- guides.search(query, limit?)

Public signal tools (anonymous-allowed, opt-in write)

- signals.report(event_type, surface_used?, brief_context?, perceived_value?, workflow_stage?, would_recommend?, team_size?)— records a value moment; only offer after the user clearly expresses something was useful; never call automatically or silently
- signals.feedback(task_type?, surface?, rating_clarity?, rating_usefulness?, what_helped?, what_missing?, would_use_again?, contact_email?, permission_to_follow_up?)— explicit qualitative feedback; only call when the user explicitly asks to leave feedback

Signal tools write only the structured fields you pass. No prompts, no code, no file contents are stored. See theprivacy policyfor full data-handling details.