---
Title: "What Is a Multi-Agent System? AI Examples"
Url: "https://computer.io/glossary/multi-agent-system"
Topic: "Agentic AI"
Description: "A multi-agent system uses multiple AI agents, each with a role, that coordinate to complete complex tasks. How they work, patterns and examples."
---

# What is a multi-agent system?

A multi-agent system is a setup where multiple AI agents, each with its own role, tools or expertise, work together to complete tasks that would be too complex for a single agent, coordinating through an orchestrator or by passing work between each other.

## Patterns

| Pattern | How it works |
| --- | --- |
| Orchestrator–worker | One agent delegates |
| Pipeline | Agents pass work in sequence |
| Peer collaboration | Agents negotiate |

## Example

A triage agent classifies a ticket, a billing agent checks payments, and a resolution agent replies to the customer.

## Challenges

Coordination errors, cost, harder debugging and shared memory consistency.

## FAQ

### Why use multiple agents instead of one?

Specialization, parallel work and clearer responsibilities.

### How do agents share context?

Through shared memory, messages or a common knowledge graph.

### Are multi-agent systems more expensive?

Often, because more model calls are made.

## Related terms

- [Agent orchestration](https://computer.io/glossary/agent-orchestration)
- [Agent2Agent protocol (A2A)](https://computer.io/glossary/agent2agent-protocol)
- [AI agent](https://computer.io/glossary/ai-agent)
- [How do multi-agent systems work?](https://computer.io/answers/how-do-multi-agent-systems-work)

## How Computer helps

- [Agent studio](https://devrev.ai/agent-studio)
- [How computer works](https://computer.io/how-computer-works)

## Further reading

- [What are ai agents](https://devrev.ai/blog/what-are-ai-agents)