Navigation

Mobile Docs

Agent Orchestrator

Coordinate multiple agents working together

Orchestrates multiple AI agents to work together on complex tasks. Supports different coordination patterns including sequential, parallel, voting, and delegation.

Agentsagent_orchestrator

Usage

01Add the block to your workflow and connect it to the upstream step.
02Configure any required credentials or tokens in the inputs.
03Fill in required inputs and optional parameters for the run.
04Run a test execution, inspect outputs, and iterate before deploying.
05Deploy the agent_orchestrator block with monitoring enabled in production.

Inputs (UI)

Agent Profile

agent-profile-selector

Layout: full

Execution Mode

dropdown

Layout: half

Options: Sync (wait for result), Async (background), Fire & Forget

Callback Webhook URL

short-input

Placeholder: https://your-server.com/callback

Layout: half

Condition: executionMode = "async"

Orchestration Pattern

dropdown

Layout: half

Options: Sequential, Parallel, Voting, Delegation

Coordinator Model

dropdown

Layout: half

Condition: orchestrationType = ["delegation","debate"]

Options: GPT-4o, GPT-5, Claude Sonnet 4.6, Claude Haiku 4.5

Coordinator Instructions

long-input

Placeholder: Instructions for how the coordinator should manage the agents...

Layout: full

Condition: orchestrationType = ["delegation","debate"]

Task

long-input

Placeholder: Describe the task for the agents to work on...

Layout: full

Agent Configuration

code

Define the agents that will participate

Placeholder: [ { "name": "Researcher", "type": "specialist", "prompt": "You are a research specialist...", "model": "gpt-4o" }, { "name": "Writer", "type": "specialist", "prompt": "You are a writing specialist...", "model": "gpt-4o-mini" } ]

Layout: full

Shared Context

code

Initial shared memory available to all agents

Placeholder: { "initialData": {} }

Layout: full

Voting Threshold

slider

Percentage of votes needed for consensus

Layout: half

Condition: orchestrationType = "voting"

Max Debate Rounds

short-input

string

Optional

Outputs

Primary response type:

{
  "result": "json",
  "agentResults": "json",
  "messages": "json",
  "consensus": "json",
  "executionOrder": "json",
  "totalDuration": "number",
  "runId": "string",
  "status": "string",
  "statusUrl": "string"
}

Tool Access

agent_orchestrator