AI Vocabulary · 05 Agents
What is Multi-Agent System?
Several AI agents with different roles working on one task, for example one researching, one writing and one reviewing.
In a multi-agent system, a task is split between several agents, each with its own instructions, context and tools. A typical pattern: a lead agent plans the work, hands parts to specialised sub-agents that research in parallel, and combines their results. Another pattern lets one agent produce and another critique.
Splitting work this way keeps each agent's context focused and allows parallel work. It also multiplies cost, makes errors harder to trace and needs careful orchestration. Many tasks are better served by one well-equipped agent.
Why it matters for you
Multi-agent setups power some of the most capable AI products, such as deep research tools. When a vendor pitches "a team of AI agents", ask what each agent does, what it costs per task and how quality is measured.
Own it
More agents mean more places for mistakes and more spending. Start simple, add agents only where you can show an improvement with evals, and keep logs of who did what.
Where it comes from
Multi-agent systems are a research field that grew out of distributed artificial intelligence in the 1980s and 1990s, studying how many independent agents cooperate, compete and negotiate (Wikipedia). Economists had studied interacting agents for much longer. Since 2023, frameworks built on large language models have given the old field a new wave of attention.
Related
Your AI Learning Hub
Learn the whole AI Vocabulary, step by step, and build with it. Build it. Own it.