Skip to content
🤖 Consolidated, AI-optimized BMAD docs: llms-full.txt. Fetch this plain text file for complete context.

How to Create Architecture

Use the architecture workflow to make technical decisions explicit and prevent agent conflicts during implementation.


  • Multi-epic projects (BMad Method, Enterprise)
  • Cross-cutting technical concerns
  • Multiple agents implementing different parts
  • Integration complexity exists
  • Technology choices need alignment

  • Quick Flow (simple changes)
  • BMad Method Simple with straightforward tech stack
  • Single epic with clear technical approach

  • BMad Method installed
  • Architect agent available
  • PRD completed

Start a fresh chat and load the Architect agent.

*create-architecture

This is NOT a template filler. The architecture workflow:

  1. Discovers technical needs through conversation
  2. Proposes architectural options with trade-offs
  3. Documents decisions that prevent agent conflicts
  4. Focuses on decision points, not exhaustive documentation

Work with the agent to create Architecture Decision Records (ADRs) for significant choices.

The agent produces a decision-focused architecture document.


An architecture.md document containing:

  1. Architecture Overview - System context, principles, style
  2. System Architecture - High-level diagram, component interactions
  3. Data Architecture - Database design, state management, caching
  4. API Architecture - API style (REST/GraphQL/gRPC), auth, versioning
  5. Frontend Architecture - Framework, state management, components
  6. Integration Architecture - Third-party integrations, messaging
  7. Security Architecture - Auth/authorization, data protection
  8. Deployment Architecture - CI/CD, environments, monitoring
  9. ADRs - Key decisions with context, options, rationale
  10. FR/NFR-Specific Guidance - Technical approach per requirement
  11. Standards and Conventions - Directory structure, naming, testing

## ADR-001: Use GraphQL for All APIs
**Status:** Accepted | **Date:** 2025-11-02
**Context:** PRD requires flexible querying across multiple epics
**Decision:** Use GraphQL for all client-server communication
**Options Considered:**
1. REST - Familiar but requires multiple endpoints
2. GraphQL - Flexible querying, learning curve
3. gRPC - High performance, poor browser support
**Rationale:**
- PRD requires flexible data fetching (Epic 1, 3)
- Mobile app needs bandwidth optimization (Epic 2)
- Team has GraphQL experience
**Consequences:**
- Positive: Flexible querying, reduced versioning
- Negative: Caching complexity, N+1 query risk
- Mitigation: Use DataLoader for batching

E-commerce platform produces:

  • Monolith + PostgreSQL + Redis + Next.js + GraphQL
  • ADRs explaining each choice
  • FR/NFR-specific implementation guidance

  • Focus on decisions that prevent agent conflicts
  • Use ADRs for every significant technology choice
  • Keep it practical - don’t over-architect
  • Architecture is living - update as you learn

After architecture:

  1. Create Epics and Stories - Work breakdown informed by architecture
  2. Implementation Readiness - Gate check before Phase 4