Navigation

Mobile Docs

Multi-Agent Collaboration

Collaborative multi-agent system

Create a collaborative multi-agent system where specialized agents work together to solve complex problems through structured communication.

Agentsmulti_agent

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 multi_agent block with monitoring enabled in production.

Inputs (UI)

Agent Profile

agent-profile-selector

Layout: full

Task

long-input

Placeholder: Enter the task or problem for the agents to solve...

Layout: full

Model

dropdown

Layout: full

Options: Dynamic options

Agents Configuration

code

Placeholder: [ { "name": "Researcher", "role": "Gathers and analyzes information related to the task", "expertise": ["data analysis", "information gathering", "critical thinking"] }, { "name": "Planner", "role": "Creates structured plans and coordinates agent activities", "expertise": ["strategic planning", "task decomposition", "coordination"] }, { "name": "Critic", "role": "Evaluates solutions and identifies potential issues", "expertise": ["critical analysis", "problem identification", "quality assurance"] } ]

Layout: full

Max Iterations

short-input

Placeholder: 10

Layout: half

Consensus Threshold

slider

Layout: half

Tools

tool-input

Layout: full

Output Format

dropdown

Layout: half

Options: Final Result Only, Full Conversation, Summary with Key Points

Knowledge Sources

knowledge-source-input

Layout: full

Max Search Results

slider

Layout: half

Condition: knowledgeSources = ""

Similarity Threshold

slider

Layout: half

Condition: knowledgeSources = ""

Enable Memory

switch

Layout: half

Memory Limit

slider

Layout: half

Condition: memoryEnabled = true

Importance Threshold

slider

Layout: half

Condition: memoryEnabled = true

Memory Tags

short-input

Placeholder: customer-support, billing, technical

Layout: half

Condition: memoryEnabled = true

Inputs (API)

agentProfileId

string

Optional

task

string

Required

model

string

Required

apiKey

string

Optional

agents

json

Required

maxIterations

number

Optional

consensusThreshold

number

Optional

temperature

number

Optional

tools

json

Optional

outputFormat

string

Optional

knowledgeSources

string

Optional

searchMaxResults

number

Optional

similarityThreshold

number

Optional

memoryEnabled

boolean

Optional

memoryLimit

number

Optional

memoryImportance

number

Optional

memoryTags

string

Optional

Outputs

Primary response type:

{
  "finalResult": "string",
  "conversation": "json",
  "model": "string",
  "tokens": "json"
}

Tool Access

function_executegoogle_searchserper_searchtavily_searchhttp_requesttext_processor