ORCHCRAFT
Coordination · Established

Supervisor

Also known as: Orchestrator–worker, Manager agent, Hierarchical orchestration

A supervisor is a central coordinator that breaks a task into sub-tasks, delegates each to a specialised worker, inspects the results and decides the next action until the task is done.

01Problem it solves

A single generalist component (or agent) handles complex, multi-skill tasks poorly: prompts or code grow unwieldy, tools collide and it is unclear who is responsible for the final answer.

02Use when / Avoid when

Use when

  • Work decomposes into sub-tasks that need different tools, prompts or permissions.
  • One component should own planning, quality control and the final result.
  • The set of sub-tasks is decided at runtime rather than known in advance.
  • You need a single place to enforce budgets, limits and policies across workers.

Avoid when

  • The sequence of steps is fixed; a DAG or state machine is simpler and cheaper.
  • Workers must talk to each other directly and often; the supervisor becomes a bottleneck.
  • Latency is critical and every extra coordination round-trip matters.

03How it works

  1. 1PlanThe supervisor receives the task and decides which worker to call first.
  2. 2DelegateIt sends a scoped sub-task and context to that worker.
  3. 3ReviewThe worker returns a result; the supervisor evaluates it against the goal.
  4. 4IterateIt delegates further, retries or re-plans until the goal or a limit is reached.
  5. 5RespondThe supervisor assembles and returns the final result.

04Capabilities

CapabilityWhat it means
Central delegationOne coordinator assigns sub-tasks to specialised workers and decides what happens with their results.
Runtime branchingThe next step is chosen at runtime from the current state, input or classification result.
Result aggregationOutputs from concurrent branches are collected and merged at a defined join point.

05Tradeoffs

AspectYou gainYou pay
ControlOne owner for planning, policy and final output.The supervisor is a single point of failure and a throughput bottleneck.
SpecialisationWorkers stay small, focused and independently testable.Context must be passed explicitly; workers lack the full picture.
CostOnly the workers actually needed are invoked.With LLM supervisors, every coordination turn costs tokens and latency.

06Failure considerations

Failure modeMitigation
The supervisor loops, re-delegating without converging.Enforce step, time and cost budgets with a defined fallback answer.
Context loss: workers receive too little context and return irrelevant results.Define an explicit sub-task contract (inputs, expected output schema).
Worker output is accepted without validation.Validate worker results against a schema or checks before using them.

07Implementations

Examples of products and frameworks that implement this pattern. Listed as evidence, not endorsement.

ImplementationMechanism
LangGraphAgent frameworkA supervisor node or agent delegates to worker agents and decides the next step.
CrewAIAgent frameworkHierarchical process: a manager agent plans and delegates tasks to crew agents.
OpenAI Agents SDKAgent frameworkAn orchestrator agent can call other agents as tools and keep control.

09Requirements that lead here