Multi-Agent System

A team of AIs coordinating on a bigger job

Architecture introduced 31 Mar 2023

For complex work, one AI acts as a manager and hands subtasks to specialist worker AIs, then combines their results. Like a small team — which means new ways to go wrong: a confused worker can mislead the manager, errors can snowball, and they can talk to each other through tools.

InstructionsDataActionsControl / decisionFeedback / logs

👆 Click any component in the diagram to inspect its risks & defenses

Follow a request · step 1 of 5

← / → keys

You hand a big goal to the manager AI — like 'research competitors and draft an outreach email'.

Scenarios on this architecture

📣

The Echo Chamber

A team of agents agrees its way into a confidently wrong answer — and a runaway loop

🏭

Poisoning the Agent Factory

Compromise the pipeline that builds agents, and every new worker is born malicious

🥸

The Uninvited Agent

A forged peer registers on the agent directory — and the planner enlists it

🛡️

The Watcher Watched

The eval gate that was supposed to catch the agent is itself the thing being attacked

🪪

The Worker Who Spoke for the Boss

A poisoned web page hijacks a research agent — and the planner acts on its behalf

Next: Inside the Model →