DamcoBook an AI Opportunity Audit

Agents should be multiplayer An agent that serves only one person builds a new silo

Arnav Gupta · 12 Oct 2026 · 5-minute read
A vintage telephone switchboard with five patch cords meeting at one jack, etched in bronze squares

Most AI agents today work for one person. You open a chat, hand it a task, and it plans the steps for you. That's useful, and it's also how a company ends up with a new silo.

Work in a business rarely belongs to one person. It moves between people, and most of its time is spent waiting.

There are three kinds of AI work

  • Automation: code decides every step. It's fast and predictable, and it stops at anything it didn't expect.
  • Single-player agents: an agent plans its own steps, for one person.
  • Multiplayer agents: an agent pursues one goal with a whole team, under its own identity.

The third kind is where the value is, because that's where the waiting happens.

One invoice touches six people

Take a supplier invoice that doesn't match its purchase order. It touches payables, purchasing, the warehouse that received the goods, the supplier, an approver, and treasury.

Give each of them an assistant, and six assistants hold six partial pictures while the invoice waits between them.

Michael Hammer described an application that spent 22 days in process and was worked on for 17 minutes. The waiting was the cost. A single-player agent can't remove waiting it can't see.

Six people, six assistantsThe invoice waits between themPayablesPurchasingWarehouseSupplierApproverTreasuryOne case, the whole teamThe agent works it, and people decideInvoice 4471PayablesPurchasingWarehouseSupplierApproverTreasury
The same supplier invoice, worked two ways.

What a multiplayer agent needs

  • It signs in as itself, with a named owner and written limits, so you always know whose account did what.
  • It knows who's on the case and who may approve what, so it asks purchasing about the order and payables about the payment.
  • It works from the same view as the people. The case, its history, and the next decision sit where both can read them.
  • Its rules live in the tools, not in its prompt. A prompt is a request, and a check inside the tool runs the same way every time.
  • Every step lands on the record, with who took it, a person or the agent.

Autonomy is earned one task at a time

Every new task starts on ask first: the agent drafts, and a person decides. When the record shows the agent gets a task right, that task can move to do alone. Some tasks stay with people for good.

Run one test before anything goes live. If every agent were switched off tonight, the business should lose only speed. No knowledge, no decision, and no record should leave with them.

Every agent needs the same way in

A multiplayer agent needs what every agent needs: a safe way into your core systems. We build that once per client as Damco Switchboard. It has tools named in your business terms, sign-in for people and agents, and rules checked in every tool.

These principles come from my longer guide on putting agents into production, which walks through all seven steps from the first sticky note to the first live case.

More from our engineers