Skip to main content
Multi-Agent Planning generates a high-level plan before distributing tasks across agents, improving coordination on complex workflows. 
from praisonaiagents import Agent, Task, PraisonAIAgents, MultiAgentPlanningConfig

researcher = Agent(name="Researcher", instructions="Research topics thoroughly.")
writer = Agent(name="Writer", instructions="Write clear, engaging content.")

tasks = [
    Task(description="Research the impact of AI on healthcare", agent=researcher),
    Task(description="Write a report on the research findings", agent=writer),
]

workflow = PraisonAIAgents(
    agents=[researcher, writer],
    tasks=tasks,
    planning=MultiAgentPlanningConfig(llm="gpt-4o", auto_approve=True),
)
workflow.start()
The user defines tasks; a planning LLM drafts a plan before agents execute.

​
Quick Start

1

Simple Usage

from praisonaiagents import Agent, Task, PraisonAIAgents, MultiAgentPlanningConfig

agent = Agent(name="Analyst", instructions="Analyze data and provide insights.")
task = Task(description="Analyze customer churn patterns", agent=agent)

workflow = PraisonAIAgents(
    agents=[agent],
    tasks=[task],
    planning=MultiAgentPlanningConfig(auto_approve=True),
)
workflow.start()
2

With Reasoning

from praisonaiagents import Agent, Task, PraisonAIAgents, MultiAgentPlanningConfig

researcher = Agent(name="Researcher", instructions="Research deeply.")
analyst = Agent(name="Analyst", instructions="Analyze and summarize findings.")

tasks = [
    Task(description="Research quantum computing use cases", agent=researcher),
    Task(description="Summarize key findings for a business audience", agent=analyst),
]

workflow = PraisonAIAgents(
    agents=[researcher, analyst],
    tasks=tasks,
    planning=MultiAgentPlanningConfig(
        llm="gpt-4o",
        reasoning=True,
        auto_approve=True,
    ),
)
workflow.start()

​
Single-Agent vs Multi-Agent Planning

PlanningConfig plans within a single agent’s execution. MultiAgentPlanningConfig plans across multiple agents and tasks.

​
How It Works

Multi-agent planning (MultiAgentPlanningConfig) generates plans at the orchestration level — it decides what tasks to run and which agents run them.This is different from single-agent PlanningConfig (see Planning Mode), which makes a single agent break down its own task into steps before acting.

​
Configuration Options

Full list of options, types, and defaults — MultiAgentPlanningConfig
OptionTypeDefaultDescription
llmstr | NoneNoneLLM for planning (defaults to workflow LLM)
auto_approveboolFalseSkip user confirmation of generated plans
toolslist | NoneNoneTools available to the planner
reasoningboolFalseEnable extended reasoning during planning

​
Common Patterns

​
Pattern 1 — Automated multi-agent research pipeline

from praisonaiagents import Agent, Task, PraisonAIAgents, MultiAgentPlanningConfig

agents = [
    Agent(name="Searcher", instructions="Search for relevant information."),
    Agent(name="Analyst", instructions="Analyze and extract insights."),
    Agent(name="Writer", instructions="Write clear, structured reports."),
]

tasks = [
    Task(description="Search for recent AI breakthroughs", agent=agents[0]),
    Task(description="Analyze which breakthroughs are most impactful", agent=agents[1]),
    Task(description="Write an executive summary", agent=agents[2]),
]

result = PraisonAIAgents(
    agents=agents,
    tasks=tasks,
    planning=MultiAgentPlanningConfig(llm="gpt-4o", auto_approve=True, reasoning=True),
).start()
print(result)

​
Best Practices

Planning requires understanding the goal and decomposing it into tasks. Use gpt-4o, claude-3-5-sonnet, or similar capable models. Smaller models often produce poor plans.
In automated workflows where human review isn’t possible, set auto_approve=True. In interactive applications, leave it False so users can review and adjust the plan before execution.
reasoning=True adds chain-of-thought prompting to the planning step, helping the planning model think through dependencies and edge cases before producing the task list.
Use multi-agent planning when you have a team of specialized agents and a complex goal that needs task decomposition. Use single-agent planning (via PlanningConfig) when a single agent needs to break down its own sub-goal.

Planning Mode

Single-agent planning configuration

Multi-Agent Execution

Configure iteration and retry limits

Multi-Agent Hooks

Intercept task lifecycle events

Autonomous Workflow

Fully autonomous multi-agent pipelines