---
title: "What Is a Multi-Agent System?"
description: "A multi-agent system splits a job across several AI agents that each own a role and coordinate, often led by an orchestrator. Meaning, how it differs from a single agent and subagents, and when to use it."
type: "glossary"
locale: "fr"
term: "Multi-Agent System"
canonical: "https://agenticschool.dev/fr/glossary/multi-agent"
dateModified: "2026-07-03"
---

# What Is a Multi-Agent System?

- Definition: Multi-Agent System
- Updated: 2026-07-03
- Keywords: multi-agent system, what is a multi-agent system, multi-agent, multi agent ai, orchestrator agent
- Canonical URL: https://agenticschool.dev/fr/glossary/multi-agent
- Locale: fr

> A multi-agent system splits a job across several AI agents that each own a role and coordinate, often led by an orchestrator. Meaning, how it differs from a single agent and subagents, and when to use it.

A multi-agent system is a setup where several AI agents, each with its own role, tools and context, work together to complete a job that would be too large or too varied for a single agent. Instead of one agent trying to do everything in one long conversation, the work is split: an orchestrator agent breaks the goal into parts and hands each part to a specialised agent (research, coding, review), then combines their results. Each agent runs in its own context so it stays focused and does not drown in the whole task at once. The pattern trades some coordination overhead for specialisation, parallelism and cleaner context, which is why it shows up in the most ambitious agentic systems.

## How multi-agent systems work

Most multi-agent systems follow an orchestrator-and-workers shape. A lead agent plans and delegates, worker agents do focused subtasks, and results flow back to be combined.

- Orchestrator: reads the goal, splits it into subtasks and decides who does what.
- Specialist agents: each owns a narrow role with its own prompt, tools and context window.
- Coordination: results are passed back and merged, sometimes across several rounds.

## Multi-agent vs single agent vs subagents

A single agent handles a whole task in one context, which is simplest and best for most jobs. Subagents are the lightweight version of going multi-agent: a main agent delegates a focused piece to a helper that runs in its own context and returns a summary. A full multi-agent system goes further, with several peer agents coordinating over a shared goal. The honest rule is to reach for more agents only when one agent genuinely cannot hold the task, because every extra agent adds coordination cost.

## When to use multiple agents

Multiple agents earn their keep when a job has distinct skills or can run in parallel: research many sources at once, or split building, testing and reviewing across specialists. They also help keep each context clean, since noisy subtasks stay out of the main thread. But more agents mean more ways to miscommunicate, so start with one capable agent and its subagents, and only grow into a full multi-agent system when the task clearly demands it.

## FAQ

### What is a multi-agent system in simple terms?

It is a setup where several AI agents, each with its own role, tools and context, work together on one goal. An orchestrator usually splits the job into parts, hands each to a specialised agent, and combines the results into a final answer.

### What is the difference between a subagent and a multi-agent system?

A subagent is a helper a main agent delegates a focused task to, running in its own context and returning a summary. A multi-agent system is broader: several agents coordinate over a shared goal. Subagents are the lightweight step toward a full multi-agent design.

### When should I use multiple agents instead of one?

Only when one agent genuinely cannot hold the task. Multiple agents help when a job has distinct skills or can run in parallel, or to keep each context clean. Otherwise a single capable agent with subagents is simpler and more reliable.

### What is an orchestrator agent?

An orchestrator is the lead agent in a multi-agent system. It reads the overall goal, breaks it into subtasks, delegates each to a specialised agent, and combines their results, acting as the coordinator rather than doing all the detailed work itself.