Subagents / agent swarm

A pattern where a main agent delegates distinct subtasks to specialized child agents, each working in its own context. A "swarm" is the same idea at larger scale, with many agents coordinating or running in parallel.

Subagents are specialized child agents that a main agent delegates distinct subtasks to, each working in its own context. A code-review agent might delegate security analysis to one subagent, performance review to another, and style checks to a third, then collect their results. Each subagent has its own context window (the information it can see), keeping it focused so one subtask cannot crowd out another. A "swarm" is the same pattern at larger scale: dozens or hundreds of agents working in parallel on different parts of a problem.

Builder example

Subagents give you speed through parallel execution and focus through scoped context. The cost is coordination complexity: subagents can produce conflicting results, duplicate work, or fail silently while the main agent moves on. Every subagent also adds token costs and makes the overall system harder to debug, since you need to trace through multiple agents to reconstruct what happened.

Common confusion: More agents does not mean a smarter system. Poorly scoped subagents multiply confusion and cost. Each one needs a clearly bounded task, a defined output format, and an owner responsible for its results.