Run by agents. Governed by humans. Where human-in-the-loop becomes runtime architecture.
The iteration loop from demo agent to production-ready: validate, read the cited doctrine, fix, re-run. Installable inside Claude Code, Cursor, and Codex via MCP.
Every score links to a public validator run.
Key Facts
- For
- Product designers, PMs, founders, AI builders, and engineers shipping agentic systems
- Handbook
- 10 principle pages connected to implementation examples and runtime architecture patterns
- Learning
- 2 course pages with linked labs and implementation references
- Practice
- 103 implementation examples mapped to principles, runtime patterns, and problem types
Works with
Watch the series
Start here, in four short videos
An introduction, then one real account, from an empty setup to a public badge: connect your coding agent, get your first score, then publish it.
Introduction
AIDB in one loop
3:01 · Ends with the whole loop seen once: doctrine, validator, review
The trio agent team
PM, Designer, Engineer: the same trio behind every real ship, one validator with the doctrine swapped. The written spec is graded on the 8 spec-quality laws, the UI surface on the 8 experience-design laws, the agent code on the 10 agentic principles. Every run returns a Blueprint Readiness Score with history per repository.
The PM Agent
Grades a written spec against the 8 spec-quality laws, testability as the floor, before anyone builds from it.
Explore the PM Agent
The Design Agent
Grades a UI surface against the 8 experience-design laws, accessibility as the floor.
Explore the Design Agent
The Architect Agent
Grades agent code against the 10 agentic principles, principle by principle.
Explore the Architect AgentLive readiness review
Two real runs, both inspectable
One we deliberately tried to break, one a real system we validated.
Try it on your code
Public repos · Validator runs on approval · Results in your account
If your agent ships any of these, the doctrine has a name for it
Four recurring failure patterns on agentic systems in production. Each one links to the principle that addresses it.
Case studies
All case studies →Blueprint Readiness Score
58/ 100
Draft
A2A reference agent: what the validator finds in our own example
Single-pass architect.validate run against aidesignblueprint/integrations, the A2A reference example + stdio proxy. 58/D, draft. Four production blockers framed as deliberate scope of a protocol demonstration, one hardening recommendation that rides a small companion fix on the integrations repo. The first case study to publish AUX-pattern annotations explicitly.
Read →Blueprint Readiness Score
22/ 100
Draft
Layer 3: applying the doctrine to claude-agent-sdk-demos
AIDB's cohort-bridge auto-bundled the email-agent SDK glue layer of anthropics/claude-agent-sdk-demos and submitted it to architect.validate. Anthropic publishes these as reference implementations for local development, not production. The validator engaged mechanism-specifically with the substrate the doctrine itself runs on top of. 22/F · high_risk · draft: seven production blockers, P8 (Approvals) at sev 95.
Read →Blueprint Readiness Score
100/ 100
Production-ready
The bridge that selects what feeds the validator, audited by the validator
Fourteen iterations of architect.validate against the cohort-bridge orchestrator that bundles applicant repositories for the validator. 35/F → 100/A. The cert reviewer confirmed the production_ready verdict on iter14: no specific missed defect that would cause silent wrong results, crash, or trust-boundary bypass.
Estimated ROI: $80K – $200K / yr
Read →Latest guides
All guides →
Deterministic orchestration, bounded tools, and evaluation before production
When your agent prototype cannot reliably finish or explain its work, Blueprint principles 6, 7, 8 and 9 help you design reliable agent workflows with enforceable boundaries.
Read →
Research is not permission to submit
When your AI agent can turn research into a live submission, Blueprint helps you design submission approval gates, observable boundaries, and inspectable controls using P5, P6, P7, and P8.
Read →
Delegate the work, not unlimited authority
Learn how to set AI agent permissions, require approval for consequential actions, and keep decisions auditable.
Read →Watch the film
Run by agents. Governed by humans.
Four machine apocalypses, one missing rule. A short film on why governance, not fear, is the answer for agentic AI.