8 min read

Multi-agent systems

It is tempting to design agents like an org chart. A planner agent, a researcher agent, a writer agent and a critic agent, passing work between them. The diagram looks sophisticated. Then the bill arrives at ten times the single agent version, the writer contradicts what the researcher found, and nobody can tell which agent made the decision that broke the output.

Multi-agent systems are genuinely powerful for some tasks and an expensive mistake for others. This chapter is about telling which is which.

Your answer

Give one task where splitting work across several agents clearly helps, and one where it clearly hurts. What is the difference between them?

What it actually means#

In practice, "multi-agent" almost always means one lead agent that hands pieces of the work to sub agents. Each sub agent gets a short brief and its own fresh context window, does its piece (often in parallel with the others), and returns a short result. The lead never sees the sub agents' working, only their conclusions.

Figure 1. Each sub agent may read 50,000 tokens to do its part and return 500. The lead's context stays small, which is the real benefit, and the total spend is the sum of all of them, which is the real cost.