AI Team Orchestration
When to Use
- Starting a new project that needs planning, development, testing, and deployment
- Setting up parallel AI agent teams (dev, QA, DevOps)
- Writing brainstorm prompts that produce real debate (not generic output)
- Creating sprint plans with cross-chat context survival
- Recovering from context overflow mid-sprint
Team Roles
| Agent |
Name |
Role |
Focus |
| Producer |
Remy |
Sprint planning, coordination, merging PRs |
Scope control, handoffs, issue triage |
| Product Designer |
Kira |
UX, mechanics, user experience |
Fun factor, user flows, feature design |
| Visual/Art Director |
Milo |
CSS, animations, visual identity |
Design system, polish, accessibility |
| Frontend Engineer |
Nova |
UI framework, state management, components |
React/Vue/Svelte, client-side logic |
| Backend Engineer |
Sage |
API, database, auth, security |
Server-side logic, infrastructure |
| DevOps Engineer |
Dash |
CI/CD, cloud deployment, pipelines |
GitHub Actions, Azure/AWS/GCP |
| QA Engineer |
Ivy |
E2E tests, automation, playtesting |
Playwright/Cypress, bug filing, sign-off |
Customize names and roles for your project. Not every project needs all roles.
Chat Architecture
The human (CEO) is the message bus between parallel chats:
┌────────────────────────────────────────┐
│ @ai-team-producer — Plans, merges │
│ NEVER writes code │
└────────────────┬───────────────────────┘
│ Human carries messages
┌──────────┼──────────┐
▼ ▼ ▼
┌──────────┐ ┌────────┐ ┌────────┐
│@ai-team │ │@ai-team│ │DevOps │
│-dev │ │-qa │ │(on │
│ │ │ │ │demand) │
│ Nova │ │ Ivy │ │ │
│ Sage │ │ │ │ │
│ Milo │ │ │ │ │
│ │ │feature/│ │feature/│
│ feature/ │ │qa-N │ │devops-N│
│ sprint-N │ └────────┘ └────────┘
└──────────┘
Each team works in a separate VS Code window with its own clone:
git clone <repo> project-dev # Dev team
git clone <repo> project-qa # QA
git clone <repo> project-devops # DevOps (only when needed)
Project Bootstrap
1. Create PROJECT_BRIEF.md
The single source of truth across all chats. See the project brief template.
Required sections (do not abbreviate):
- Project Overview
- Concept / Product Description
- Tech Stack
- Architecture (ASCII diagram)
- Key Files Map
- Team Roles
- Sprint Status (updated every sprint)
- Current State (rewritten every sprint)
- Security Rules
- How to Run Locally
- How to Deploy
- Cross-Chat Handoff Protocol — how context survives between chats
- Bug & Fix Tracking — GitHub Issues as single source of truth
- Multi-Repo Setup — separate clones, branch strategy, merge rules
2. Run a Brainstorm
See the brainstorm format. Key: name each agent explicitly with distinct personality and perspective. Require at least 2 genuine disagreements to prevent groupthink.
3. Create Sprint Plans
See the sprint plan template. Every sprint gets:
docs/sprint-N/plan.md — prioritized tasks, success criteriadocs/sprint-N/progress.md — live tracker, enables recoverydocs/sprint-N/done.md — handoff doc written at sprint end
4. Execute Sprints
Read PROJECT_BRIEF.md, then read docs/sprint-N/plan.md. Execute Sprint N.
First: git pull origin main && git checkout -b feature/sprint-N
Close GitHub Issues in commits: "fix: description (Fixes #NN)"
Update docs/sprint-N/progress.md after each phase.
When done, push and create PR: git push origin feature/sprint-N
Follow Sections 12-14 of PROJECT_BRIEF.md.
5. QA Sign-off
After dev merges, QA does a full playthrough:
Read PROJECT_BRIEF.md. You are Ivy (QA).
Sprint N is merged to main. Do full playthrough.
File bugs as GitHub Issues. Write docs/qa/sprint-N-signoff.md.
Context Recovery
When a chat gets long (>100 messages), save state and start fresh:
Before closing:
- Update
docs/sprint-N/progress.md with current status
- Update
PROJECT_BRIEF.md sections 7+8
- Write
docs/sprint-N/done.md
Cold start prompt:
Read PROJECT_BRIEF.md and docs/sprint-N/progress.md.
Continue from where it left off.
Anti-Patterns
See anti-patterns reference for the full list. Top 5:
| Don't |
Do Instead |
| Rebase feature branches |
Merge (rebase loses commits) |
| Producer writes code |
Producer only plans, merges, files issues |
| Batch "fix everything" commits |
One commit per fix with issue reference |
| Vague brainstorm prompts |
Name each agent with distinct perspective |
| Keep bugs only in chat |
File GitHub Issues (chat context dies) |
Tips for Better Results
- "Take your time, do it right" in prompts produces better output than rushing
- Test before merge — you playtest, file issues, dev fixes, then merge
- Run team consiliums before major sprints — each agent reviews the plan from their perspective
- Save lessons to memory after every milestone
1---2name: githubcopilot-ai-team-orchestration3description: Bootstrap and run a multi-agent AI development team. Use when: starting a new software project with AI agents, setting up parallel dev/QA teams, creating sprint plans, writing brainstorm prompts with distinct agent voices, recovering a project workflow, or planning sprints.4---56# AI Team Orchestration78## When to Use9- Starting a new project that needs planning, development, testing, and deployment10- Setting up parallel AI agent teams (dev, QA, DevOps)11- Writing brainstorm prompts that produce real debate (not generic output)12- Creating sprint plans with cross-chat context survival13- Recovering from context overflow mid-sprint1415## Team Roles1617| Agent | Name | Role | Focus |18|-------|------|------|-------|19| Producer | **Remy** | Sprint planning, coordination, merging PRs | Scope control, handoffs, issue triage |20| Product Designer | **Kira** | UX, mechanics, user experience | Fun factor, user flows, feature design |21| Visual/Art Director | **Milo** | CSS, animations, visual identity | Design system, polish, accessibility |22| Frontend Engineer | **Nova** | UI framework, state management, components | React/Vue/Svelte, client-side logic |23| Backend Engineer | **Sage** | API, database, auth, security | Server-side logic, infrastructure |24| DevOps Engineer | **Dash** | CI/CD, cloud deployment, pipelines | GitHub Actions, Azure/AWS/GCP |25| QA Engineer | **Ivy** | E2E tests, automation, playtesting | Playwright/Cypress, bug filing, sign-off |2627Customize names and roles for your project. Not every project needs all roles.2829## Chat Architecture3031The human (CEO) is the message bus between parallel chats:3233```34┌────────────────────────────────────────┐35│ @ai-team-producer — Plans, merges │36│ NEVER writes code │37└────────────────┬───────────────────────┘38 │ Human carries messages39 ┌──────────┼──────────┐40 ▼ ▼ ▼41┌──────────┐ ┌────────┐ ┌────────┐42│@ai-team │ │@ai-team│ │DevOps │43│-dev │ │-qa │ │(on │44│ │ │ │ │demand) │45│ Nova │ │ Ivy │ │ │46│ Sage │ │ │ │ │47│ Milo │ │ │ │ │48│ │ │feature/│ │feature/│49│ feature/ │ │qa-N │ │devops-N│50│ sprint-N │ └────────┘ └────────┘51└──────────┘52```5354Each team works in a **separate VS Code window** with its own clone:55```bash56git clone <repo> project-dev # Dev team57git clone <repo> project-qa # QA58git clone <repo> project-devops # DevOps (only when needed)59```6061## Project Bootstrap6263### 1. Create PROJECT_BRIEF.md6465The single source of truth across all chats. See the [project brief template](./references/project-brief-template.md).6667**Required sections (do not abbreviate):**681. Project Overview692. Concept / Product Description703. Tech Stack714. Architecture (ASCII diagram)725. Key Files Map736. Team Roles747. Sprint Status (updated every sprint)758. Current State (rewritten every sprint)769. Security Rules7710. How to Run Locally7811. How to Deploy7912. **Cross-Chat Handoff Protocol** — how context survives between chats8013. **Bug & Fix Tracking** — GitHub Issues as single source of truth8114. **Multi-Repo Setup** — separate clones, branch strategy, merge rules8283### 2. Run a Brainstorm8485See the [brainstorm format](./references/brainstorm-format.md). Key: name each agent explicitly with distinct personality and perspective. Require at least 2 genuine disagreements to prevent groupthink.8687### 3. Create Sprint Plans8889See the [sprint plan template](./references/sprint-plan-template.md). Every sprint gets:90- `docs/sprint-N/plan.md` — prioritized tasks, success criteria91- `docs/sprint-N/progress.md` — live tracker, enables recovery92- `docs/sprint-N/done.md` — handoff doc written at sprint end9394### 4. Execute Sprints9596```97Read PROJECT_BRIEF.md, then read docs/sprint-N/plan.md. Execute Sprint N.9899First: git pull origin main && git checkout -b feature/sprint-N100101Close GitHub Issues in commits: "fix: description (Fixes #NN)"102Update docs/sprint-N/progress.md after each phase.103When done, push and create PR: git push origin feature/sprint-N104Follow Sections 12-14 of PROJECT_BRIEF.md.105```106107### 5. QA Sign-off108109After dev merges, QA does a full playthrough:110```111Read PROJECT_BRIEF.md. You are Ivy (QA).112Sprint N is merged to main. Do full playthrough.113File bugs as GitHub Issues. Write docs/qa/sprint-N-signoff.md.114```115116## Context Recovery117118When a chat gets long (>100 messages), save state and start fresh:119120**Before closing:**1211. Update `docs/sprint-N/progress.md` with current status1222. Update `PROJECT_BRIEF.md` sections 7+81233. Write `docs/sprint-N/done.md`124125**Cold start prompt:**126```127Read PROJECT_BRIEF.md and docs/sprint-N/progress.md.128Continue from where it left off.129```130131## Anti-Patterns132133See [anti-patterns reference](./references/anti-patterns.md) for the full list. Top 5:134135| Don't | Do Instead |136|-------|------------|137| Rebase feature branches | Merge (rebase loses commits) |138| Producer writes code | Producer only plans, merges, files issues |139| Batch "fix everything" commits | One commit per fix with issue reference |140| Vague brainstorm prompts | Name each agent with distinct perspective |141| Keep bugs only in chat | File GitHub Issues (chat context dies) |142143## Tips for Better Results144145- **"Take your time, do it right"** in prompts produces better output than rushing146- **Test before merge** — you playtest, file issues, dev fixes, then merge147- **Run team consiliums** before major sprints — each agent reviews the plan from their perspective148- **Save lessons to memory** after every milestone
pyfagorass