orchestrator-workers
A pattern in which a lead model breaks a task into subtasks at run time, hands them to worker calls or sub-agents, and combines their results.
In more detail
Unlike sectioning, the subtasks are not known in advance. Give every worker a brief with its objective, output format, tools and boundaries, and expect several times the tokens of a single agent.
Related terms
- sub-agent — An agent started by another agent to do one piece of work in its own fresh context, returning only its finding.
- multi-agent system — Several agents with separate contexts and roles working on one task, coordinated by a lead or by handing work to each other.
- workflow (LLM) — A system in which your code fixes the sequence of model calls and tools, as opposed to an agent that chooses its own steps.
Taught in
- When Context Fails — AI Engineering: LLM Apps, RAG & Agents
- Workflows Before Agents — AI Engineering: LLM Apps, RAG & Agents
- Planning, Memory And Many Agents — AI Engineering: LLM Apps, RAG & Agents