Multi-agent systems
Several agents with different roles or contexts work together on one task.
Read first: The agent loop.
D1 · StoryFor young children and total beginners
Big jobs are easier with a team: one person plans, others do the parts, and someone checks the work.
Multi-agent systems are teams of AIs.
Like: A team with a planner, workers and a checker.
D2 · PictureFor curious beginners
An orchestrator agent splits a task and hands pieces to sub-agents, each with its own instructions and context window.
Sub-agents return summaries rather than everything they saw, which keeps the orchestrator's context focused.
Benefits: parallel work and separation of concerns. Costs: more tokens, coordination errors and harder debugging.
Like: A team with a planner, workers and a checker.
Where it breaks: Human teammates share background knowledge. Sub-agents share nothing except what's written in their instructions, so vague hand-offs fail silently.
D5 · FrontierFor experts
Open problems: when multi-agent setups beat one strong agent, communication protocols between agents (such as A2A), and agents amplifying each other's mistakes.