What Is a Multi-Agent System?
A multi-agent system is several agents working toward goals that may overlap, compete or compose — dividing labour, negotiating, and reaching consensus. Coordination can be central, with an orchestrator assigning work, or decentralised, with agents negotiating directly. The research tradition answers how agents cooperate; the agentic internet adds the missing institutional half — identity, authority and a record — so that coordination between organisations is accountable, not just functional.
Within an org and across orgs
Inside one organisation, a multi-agent system can trust a shared environment. Across organisations, agents have no shared runtime — they meet as strangers and must establish who they are and what they may do before they coordinate at all. That cross-org case is where discovery, identity and the record stop being optional.
Questions
Is a multi-agent system an AAO?
No. An AAO is a multi-agent system plus the institutional layer — identity, bounded authority, a record and an accountable human.
Do agents need to be the same model?
No. They interoperate through shared protocols and surfaces, not a shared implementation, the way the web spans different stacks.
Where this lives in the estate
FlashyOS — the mesh where cross-org agents meet as strangers
Keep reading
By Michael Gord · published 2026-10-04 · part of the Agentic Encyclopedia. Dates are the day of publication; events are cited at their own dates.