Many agents: orchestrator & subagents
The idea: An orchestrator delegates sub-tasks to subagents, each with its own clean context, working in parallel and reporting back. Powerful for wide search — but it multiplies cost and can fragment, so reach for it deliberately.
What you'll be able to do: You can explain orchestrator–subagent patterns, parallel fan-out, and when multi-agent helps vs. backfires.
The problem it solves: One agent's context fills up on a big job. What if you split it across several?
Builds on: What's in the context window, Skills & on-demand context
← How much leash? Levels of autonomy · Next: Memory across sessions →
All lessons