← All artifacts · All patterns · Multi-Agent

Orchestrator-Workers

aka Dynamic Decomposition, Orchestrator-Subagents

category: multi-agent · status: mature

Intent

An orchestrator dynamically breaks a task into subtasks at runtime and delegates each to a worker LLM, then synthesises results.

Context

The subtasks needed are not known in advance and depend on the task; coding tasks where the number of files to change varies are the canonical example.

Problem

Static decomposition (Plan-and-Execute, Prompt Chaining) cannot handle tasks whose shape is data-dependent.

Forces

• The orchestrator must reason at a higher level than any worker.
• Workers should not have to know they are workers.
• Synthesis must reconcile conflicting worker outputs.

Solution

Orchestrator agent receives the task, decides at runtime what subtasks to spawn, hands each to a worker (often via tool call), collects results, and synthesises the final output. Worker count and roles can vary per task.

Constrains

Consequences

Benefits

• Handles tasks with data-dependent decomposition.
• Workers stay simple; complexity lives in the orchestrator.

Liabilities

• Orchestrator failure is unrecoverable without retry logic.
• Token cost scales with worker count; budget awareness matters.

Known Uses

• Anthropic Building Effective Agents (Workflow #4)
• Claude Code subagents
• Anthropic Multi-Agent Research
• OpenAI Deep Research

Related Patterns

• alternative-to → supervisor
• alternative-to → plan-and-execute
• generalises → subagent-isolation
• generalises → lead-researcher
• complements → inter-agent-communication
• generalises → hierarchical-agents
• complements → dynamic-expert-recruitment
• generalises → agent-as-tool-embedding

References

• Anthropic: Building Effective Agents (2024) blog