Single-agent systems hit practical limits. A long task may require research, planning, implementation, review, execution, and synthesis. Putting all of that into one prompt and one context window can create overloaded state, weak verification, and behavior that is hard to debug.

A multi-agent design splits the work across specialized agents with explicit handoffs.

A multi-agent system uses several agents to work on a larger task. Each agent owns a role, toolset, context, or phase of the workflow. One agent may collect source material, another may draft, another may check claims, and a supervisor may decide when the result is ready.

This does not make the system reliable by itself. Multi-agent systems add coordination cost, latency, and new failure modes. They are useful when specialization, parallelism, independent review, or context isolation is worth that overhead.

This chapter covers the patterns that matter in practice: supervisor-worker, peer-to-peer loops, debate and critique, structured handoffs, and the criteria for choosing a multi-agent design over a simpler single-agent system.