How agents work
The loop inside every agent, how agents work with each other, and when several agents are worse than one.
6 chapters · 24 min
Start the course- 1The loop inside every agentAn agent is a model using tools in a loop. Everything else, from memory to multi-agent systems, is built on those few steps.4 min
- 2Tools decide what an agent can doAn agent can only act through its tools, and it only understands them through their descriptions. Good tools are few, clearly named, short in what they return, and honest about errors.4 min
- 3Context is a budget, memory lives outside itAn agent's attention is finite and gets worse as the window fills. Keep only what matters in view, load the rest when needed, and write long-term state to files.4 min
- 4How agents work with each otherAgents cooperate in three shapes: a lead that hands out work, a maker checked by a separate evaluator, and peers sharing a repository. In all three, files carry the messages.4 min
- 5When many agents are worse than oneParallel agents win on broad, read-heavy research and often lose on coding, where the pieces share assumptions. The cost is real: about 15 times the tokens of a chat.4 min
- 6How to tell whether an agent is any goodJudge an agent by what it leaves behind, not by the steps it took. Start from real failures, mix cheap graders with calibrated ones, and suspect the test before the agent.4 min