How Agents Talk to Each Other

In multi-agent systems, the way agents share information is as important as the agents themselves. Poor communication patterns lead to lost context, infinite loops, and token explosions.

Communication Patterns

Shared Blackboard Pattern

// Shared Blackboard Architecture
const blackboard = {
  goal: "Write a technical blog post about RAG",
  research: null,    // ResearcherAgent writes here
  outline: null,     // PlannerAgent writes here  
  draft: null,       // WriterAgent writes here
  feedback: null,    // ReviewerAgent writes here
  status: "researching"
};

// Each agent reads the blackboard, does its job, writes back:
while (blackboard.status !== "complete") {
  const activeAgent = selectAgent(blackboard.status);
  await activeAgent.process(blackboard);
}

The Token Cost Problem

Every time agents communicate, you're burning tokens. A naive 4-agent system that passes full context between agents can use 10-50x more tokens than a single agent. Mitigation strategies:

• Summarize before passing: Agent A sends a summary, not its full output.
• Structured handoffs: Use JSON objects with specific fields, not prose.
• Lazy loading: Agents only request context they actually need.