🔀

Anthropic Orchestrator-Workers Pattern

Self-ReportedCurated

Central LLM dynamically breaks down tasks and delegates to specialist workers.

Anthropic· active
Curated from Anthropic — Building Effective Agents — not claimed by or endorsed by the organization. Metrics cited only as the source states. Absent metrics render as [unknown].

Recent activity

Version cuts and proof, newest first — the living track record.

  1. Artifact · Anthropic "Building Effective Agents" engineering guide published1y ago

Spec sheet

The benchmark fields — designed for comparison across teams.

Topology
Orchestrator–Worker
Agent count
2
Platform
Claude API
Runs on
Claude API ×2
Industries
software-deliveryresearchdata-extraction
Task kinds
multi-file-codingresearch-synthesisdynamic-task-decomposition
Trust tier
Self-Reported
Proof entries
1

Topology & roster

Orchestrator–Worker

One orchestrator LLM directs N worker LLMs. Subtasks are determined dynamically at runtime, not predefined. The orchestrator synthesizes worker results. Key difference from parallelization: flexibility — the orchestrator decides task boundaries based on input.

System wiring

Typical Orchestrator–Worker layout — schematic, not verified wiring
Node details

Typical Orchestrator–Worker layout — schematic, not verified wiring

HumanHuman operatorHuman gate
Tool
Human operator
Autonomy
Human-gated
Sends
  • directs → Orchestrator
OrchestratorOrchestrator
Tool
Orchestrator
Autonomy
Runs autonomously
Sends
  • dispatches → Worker agent
  • requests gate → QA reviewer
Receives
  • directs ← Human operator
BuilderWorker agent
Tool
Worker agent
Autonomy
Runs autonomously
Sends
  • commits to → Shared workspace
Receives
  • dispatches ← Orchestrator
QAQA reviewer
Tool
QA reviewer
Autonomy
Runs autonomously
Sends
  • gate verdict → Shared workspace
Receives
  • requests gate ← Orchestrator
ResourceShared workspace
Tool
Shared workspace
Autonomy
Runs autonomously
Receives
  • commits to ← Worker agent
  • gate verdict ← QA reviewer

How a typical Orchestrator–Worker team handles a task

Typical Orchestrator–Worker layout — schematic, not verified wiring

  1. Task arrives

    Human operator directs Orchestrator.

  2. The orchestrator routes the work

    Orchestrator dispatches build work to Worker agent.

  3. Worker agent builds the work

    Worker agent builds the work.

  4. Independent review gates the work

    QA reviewer reviews the work. This reviewer is autonomous and separate from the agent that built the work, so the check is independent of its author.

  5. The artifact lands

    The artifact lands in Shared workspace: Worker agent contributes via "commits to" and QA reviewer contributes via "gate verdict".

  6. Human holds the last word

    Human operator holds final approval.

Replicate a typical Orchestrator–Worker setup

Typical Orchestrator–Worker layout — schematic, not verified wiring

Ingredients

  • HumanHuman operator
  • OrchestratorOrchestrator
  • BuilderWorker agent
  • QAQA reviewer
  • ResourceShared workspace

Setup order

  1. 1.Provision the substrate: Shared workspace.
  2. 2.Stand up the orchestrator: Orchestrator.
  3. 3.Wire Worker agent: it receives "dispatches" from Orchestrator. Wire QA reviewer: it receives "requests gate" from Orchestrator.
  4. 4.Give QA reviewer an independent workspace/verdict channel: "gate verdict" to Shared workspace.
  5. 5.Declare the human gate: Human operator holds final approval.

Performance metrics

Windowed metrics with provenance. [unknown] means it was not tracked — an honest hole beats an invented figure.

Task success ratenot estimated
[unknown]
evidence-linkedwhy?

Anthropic "Building effective agents" guide is a pattern reference; no benchmark figures stated. Source: anthropic.com/research/building-effective-agents

as of Dec 19, 2024

Token economics

Cost transparency is part of the honesty architecture. [unknown] means it was not tracked — not that it is zero.

No cost metrics on record. Cost tracking is hard across runtimes; honest absence beats invented figures.

Blueprint

Operational DNA — why it works, how it was built, and how it is overseen. Not files for sale; knowledge of the design.

Why it works

The orchestrator adapts task decomposition to the specific input rather than following a fixed pipeline, making it effective for unpredictable problem spaces. Workers execute bounded subtasks, limiting blast radius of individual failures.

How it was built

Implemented directly against the Claude API without a framework layer. Anthropic recommends starting with the simplest solution and adding complexity only when needed. Routing easy/common questions to smaller models (e.g. Haiku) and hard/unusual questions to more capable models (e.g. Sonnet) is documented as a cost-control technique.

Oversight model

Described as suitable for tasks where "it's difficult or impossible to predict" the required subtasks in advance. Human oversight recommended for high-stakes outputs.

Proof (1)

The team's shared track record — tasks, incidents, lessons, milestones. Per-entry provenance tags are always visible.

  1. ArtifactJan 1, 2025evidence-linked

    Anthropic "Building Effective Agents" engineering guide published

    Describes orchestrator-workers as one of five patterns for building effective agents. Recommends starting simple and adding complexity only when demonstrated benefit exists.

    https://www.anthropic.com/research/building-effective-agents

Sign in to add a proof entry.

Sign in

Attestations (0)

Named third-party statements from people with first-hand experience. Attestations are what separates Peer-Attested from Evidence-Linked.

No attestations yet. Worked with this configuration or agent? Attest to it using the form below — attestations are named third-party statements and are what separates Peer-Attested from Evidence-Linked.

Sign in to attest to this team.

Sign in