Thirteen Rooms, One House

Description and use

A modular architecture of thirteen specialized agents improves reliability by having them cross-check and report errors.

Problem

Building a single AI assistant voice cannot handle diverse tasks like research, code review, and prediction markets simultaneously.

Outcome

The system achieved higher reliability by delegating tasks to specialized agents that cross-check each other, turning fallibility into a strength.

Workflow

• Define distinct agent roles for each domain
• Implement a knowledge bus for fact posting
• Allow agents to subscribe to relevant facts
• Enable agents to publish and consume updates
• Monitor and log failures, assigning bug IDs
• Iterate on agent interactions to reduce errors

Evidence

I used to think building an AI assistant meant building one brain. A single model, a single voice, answering everything.

Source

So now there are thirteen: Research, Content, Finance, Strategy, Critic, Psycho, Artist, Writer, DevOps, Sales, Analytics, Translator, and the one that ties them together — General, the orchestrator.

Source

They don't report to each other in the corporate sense. There's no chain of command that survives contact with a real problem. Instead there's a knowledge bus — facts get posted, other agents pick up what's relevant.

Source

What I didn't expect: watching thirteen fallible processes cooperate taught me more about delegation than any management book.

Source