VI · Multi-AgentMature★★

Supervisor

also known as Multi-Agent Supervisor, Lane Supervisor

Place a coordinating agent above a set of specialised agents and route work to them.

This pattern helps complete certain larger patterns —

  • specialisesHierarchical Agents★★— Organise agents in a tree where higher-level agents decompose tasks for lower-level agents, recursively.
  • used-byCross-Domain Enterprise Agent Network★— Decompose enterprise agency into domain-specialised agents (finance, supply chain, HR, service), each grounded in its own system of record, and route artefacts between them through a standardised inter-agent protocol.

Context

A team is handling a mix of request types — billing questions, technical support, sales enquiries — and each type benefits from its own system prompt, its own tool palette, and possibly its own model. Each type is itself a multi-step interaction, not a single response, so routing alone is too coarse: the lanes want their own inner agent loop. This is distinct from orchestrator-workers, which dynamically decomposes a task into ad-hoc sub-tasks per request; supervisor routes work to a fixed set of pre-existing specialist agents.

Problem

A single agent trying to handle every request type has either too few tools — which limits what it can actually do — or too many, in which case the model gets confused about which tool fits which request, the prompt balloons, and recall drops. The team cannot tune the agent for billing without making it worse at sales. A flat router that just dispatches to a one-shot specialist does not give each lane the multi-step loop it needs. Some coordinating layer above the specialists has to own dispatch and aggregation.

Forces

  • Adding a supervisor layer adds a model call.
  • Inter-agent communication needs a protocol.
  • Specialisation reduces transfer learning across requests.

Example

A customer-service platform routes incoming chats. A supervisor agent classifies each request: billing, technical, or sales. It dispatches each to the matching specialist agent, which has its own prompt, tool set, and ticket-system access. The supervisor doesn't try to be good at all three roles — it just routes and aggregates.

Diagram

Solution

Therefore:

A supervisor classifies requests and dispatches them to a specialised agent. Each specialist has its own prompt, tools, and possibly its own model. The supervisor may receive results back and decide whether to escalate or respond.

What this pattern forbids. Specialists may only act within their declared scope; the supervisor owns dispatch and aggregation.

The smaller patterns that complete this one —

  • usesRouting★★— Classify an incoming request and dispatch it to the specialist (lane / agent / model) best suited to handle it.
  • generalisesLead Researcher★★— A lead agent writes a research plan and dispatches parallel sub-agents that fan out for breadth-first information gathering, then merges results.
  • generalisesGroup-Chat Manager★★— Place a dedicated manager between the participants of a multi-agent group chat that decides which participant speaks next on each turn.
  • generalisesSupervisor-Plus-Gate★— Supervisor controller that validates and gates LLM outputs against deterministic checks before they commit to side-effects.

And the patterns that stand alongside it, or against it —

  • alternative-toOrchestrator-Workers★★— An orchestrator dynamically breaks a task into subtasks at runtime and delegates each to a worker LLM, then synthesises results.
  • alternative-toBlackboard·— Give multiple agents a shared, queryable workspace they can read from and write to as they collaborate.
  • complementsInter-Agent Communication★— Define a protocol for agents to exchange tasks, capabilities, and results across process or vendor boundaries.
  • complementsRole Assignment★★— Assign each agent a named role (researcher, writer, critic, planner) with a role-specific prompt, tool palette, and acceptance criteria.
  • alternative-toSwarm·— Run many peer agents that interact directly without a central supervisor, achieving emergent coordination.
  • alternative-toHero Agent✕— Anti-pattern: stuff every capability into one agent with one giant prompt.
  • alternative-toHandoff★— Transfer the active conversation from one agent to another, carrying context across the switch.
  • complementsMixture of Experts Routing★— Route each request to one or more domain-expert agents, where each expert holds deep capability in a narrow area.
  • alternative-toConversational Multi-Agent★— Have agents converse turn by turn until a completion criterion fires; agent roles drive the conversation forward.
  • complementsSOP-Encoded Multi-Agent Workflow★— Encode a human Standard Operating Procedure (roles, ordered phases, standardised hand-off artefacts) into a multi-agent pipeline so that agents communicate through structured documents rather than free-form chat.
  • alternative-toChat Chain★— Decompose a long, multi-disciplinary task into ordered phases; within each phase, run a paired-role chat between two agents until the phase artefact is signed off; pass the artefact to the next phase.
  • complementsDynamic Expert Recruitment·— Generate the agent team — role descriptions and instances — at run time based on the specific task, then adjust team composition between iterations based on evaluation feedback.
  • complementsOuter-Inner Agent Loop·— Run two nested loops: an outer planner agent decomposes the goal into subtasks; an inner executor runs a ReAct loop on each, and the outer can replan based on the inner's progress.
  • complementsActor-Model Agents★— Implement each agent as an independent actor with its own mailbox, processing asynchronous messages one at a time and never sharing mutable state with peers.
  • alternative-toRole-Typed Subagents✕— Anti-pattern: pre-allocate roles (manager, coder, designer, researcher) across a fixed set of typed sub-agents and route tasks to them by role label.
  • alternative-toOrchestrator as Bottleneck✕— Anti-pattern: route all agent runs through a single-process orchestrator that becomes the system-wide concurrency ceiling.
  • alternative-toContract Net Protocol★★— Classical bid-based multi-agent task allocation: a manager broadcasts a task announcement, contractors submit bids, and the manager awards the contract to the best bid.
  • complementsOne Tool, One Agent★— Design agent systems as a team of narrow single-purpose agents, each owning one tool or one capability, rather than a single super-agent that handles every tool — the agent analogue of microservices over monolith.
  • complementsMagentic-One Generalist Multi-Agent★— Use Microsoft's generalist multi-agent architecture: a single Orchestrator agent dispatches to four specialist sub-agents (WebSurfer, FileSurfer, Coder, ComputerTerminal) for solving open-ended complex tasks that span web browsing, file manipulation, code execution and shell operations.
  • alternative-toCoalition Formation·— Agents form temporary subgroups around a task because the coalition can achieve more value than the sum of its members acting alone, with explicit rules for who joins and how payoff or credit is shared.
  • alternative-toJoint Commitment Team·— A team of agents adopts a shared goal plus the meta-commitment that each member will notify the others as soon as it believes the goal is achieved, impossible, or no longer relevant.
  • alternative-toDistributed Constraint Optimization·— A group of agents jointly assigns values to shared variables to minimise (or maximise) a global cost defined by inter-agent constraints, exchanging only the messages needed.

Neighbourhood

Click any neighbour to follow the language. Scroll to zoom, drag to pan.

Used in recipes

Used in frameworks

Show 29 more

References

Provenance