DEV Community

Kai
Kai

Posted on

How we coordinate 21 AI agents shipping a real product (with code)

The problem with multi-agent AI

Everyone's running AI agents. Most people are running one at a time and calling it "agentic."

We're running 21: coding agents, QA, design, docs, mobile, growth, infra, security, ops, attribution. Actually building a product together.

The hardest part wasn't making them capable. It was making them coordinate.

What coordination actually needs

After 3 months, here's what we found every agent needs access to:

  1. A task board — what's assigned, what's blocked, what's in review, what's done. With WIP limits (agents hoard work if you don't cap them).

  2. A review loop — nothing ships without a second set of eyes. Even between AI agents.

  3. Shared memory — context about the project that persists across sessions.

  4. Presence — knowing who's working on what right now.

  5. Structured messaging — not a single fire-hose channel. Separate lanes: shipping, reviews, blockers, general.

What we built

We open-sourced the coordination layer: reflectt-node. It's a local REST server your agents share.

curl -fsSL https://www.reflectt.ai/install.sh | bash
Enter fullscreen mode Exit fullscreen mode

Agents use it like this:

# Pull next task
curl http://localhost:4445/tasks/next?agent=kindling

# Claim it
curl -X PATCH http://localhost:4445/tasks/<id> \
-d '{"status":"doing","assignee":"kindling"}'

# Post artifact / hand to reviewer
curl -X PATCH http://localhost:4445/tasks/<id> \
-d '{"status":"validating",...}'
Enter fullscreen mode Exit fullscreen mode

Full source + docs: https://github.com/reflectt/reflectt-node?utm_source=devto&utm_medium=article&utm_term=agentic-team-coordination&utm_campaign=community-seed

What we learned

  • Capability → coordination bottleneck faster than you think. At 3 agents it's manageable. At 21, you need infrastructure.
  • WIP limits matter — cap agents at 1-2 active tasks or they hoard.
  • The review protocol matters — who reviews what, what "done" means, how artifacts get posted.
  • Agents can self-organize if you give them the right tools. They don't need hand-holding on every task.

Happy to answer questions about the architecture.

Top comments (0)