Skip to content

Multi-Agent Orchestration

Build entire SaaS platforms by coordinating specialist agents with the /orchestrate workflow.


Most AI interactions are 1-on-1. The orchestrator agent changes this by acting as a Project Manager. It breaks down a large request (e.g., “Build a SaaS MVP”) into tasks and assigns them to the best specialist for the job.

Backend
API & DB Architect
Frontend
UI/UX Specialist
Security
Safety Auditor
QA
Test Engineer

1

Project Brief

Describe the high-level goal. The orchestrator will interview you to clarify requirements.

Terminal window
/orchestrate Build a "Course Platform" MVP with:
- User Authentication (Auth.js)
- Stripe Payments
- Video Hosting (Mux)
- Dashboard for Instructors
2

Phase 1: Planning

The project-planner agent creates a detailed roadmap ({task-slug}.md in the project root).

…

  • Users (id, email, role)
  • Courses (id, title, price)
    …
3

Phase 2: Execution

Agents work in parallel. The Orchestrator monitors progress and unblocks dependencies.


agent-session
$
/orchestrate Build E-commerce MVP

▸
Activating Squad…
Assigning tasks based on the ecommerce-mvp.md plan:

Backend-Specialist:Configuring Prisma Schema…
Frontend-Specialist:Building ProductCard component…
Security-Auditor:Reviewing auth flow…

▸
✅ Project Complete!
All tasks finished. Run bun run dev to start.


💡

Start Small

Don’t try to build Facebook in one go. Orchestrate an MVP first, then use /enhance to iterate.

💡

Define Auth

Always specify how users log in (e.g., “Use Auth.js with GitHub”). It’s a key architectural decision.