A small team adds three agents and the week gets slower. Inbox noise goes up. Finished work goes down. Someone says the models are not good enough. Usually the models are fine. The team never installed a protocol.
The coordination gap
Capability is cheap. A specialist agent that drafts, files, or researches can be standing by evening.
Coordination is expensive. Who holds the goal at the boundary. What context travels. What must be reviewed. How the board updates. How the team sees state on Monday.
Agent orchestration is that work. A graph of model calls is not. If you cannot point at the packet that crossed a boundary, you did not orchestrate. You launched.
This is why “we tried multi-agent” often means “we tried a swarm demo.” The demo can look busy. The org cannot see who owns the output.
Where it breaks
Four boring breaks, in the order I see them.
Handoff. The first agent finishes. The second starts from a chat log. Constraints die in the paste. A six-field packet (goal, constraints, inputs, provenance, acceptance, deadline) would have been enough.
Review. Output ships because it sounded right. There is no written acceptance line. The human in the loop is a spectator.
Update. The world moved. The agent roster did not. Old tools, old prompts, old customer facts.
Sync. Standup becomes a tour of model traces. A dashboard would have done it. The meeting exists because nobody can see state.
Named failure is fixable. “Agents disappointed us” is not.
What CHORUS is for
CHORUS is a six-skill protocol: Charter, Handoff, Orchestrate, Review, Update, Sync. It is for teams of 2 to 15 who already mix humans and specialised agent workers. It is not a CrewAI tutorial and not a graph product.
The Multi-Agent Organization is the book. The introduction is the book page in article form. This piece is only the gap: why the team got slower, and which missing skill did it.
If you install one triangle first, install this one: charter every role, one real review gate, one weekly sync that is not a standup tour. Ninety days. Then add agents, not before.
A ten-minute diagnostic
List every agent that touched work last week. For each one, write the last human who accepted its output. If you cannot name that person, you found the gap. Fill the charter before you add the fourth agent.