Guides
Guides to working with AI agents as a team
Working with an AI agent as a team takes five practices a private chat does not support: handing a session off, steering it while it runs, reviewing results before they count, keeping long tasks running, and sharing what agents learn. Each guide below explains one practice in general terms first.
What are multiplayer AI agents?
A multiplayer AI agent is an agent session that a whole team shares instead of one person's private chat. Anyone on the team can drop into the same live session to watch the agent work, redirect it while it runs, hand it off to a colleague, and approve the result, with every step kept in one place.
How to hand off an AI agent session to a teammate
AI agent handoff is passing ownership of a running agent session to a teammate or to another agent without losing the work already done. A good handoff moves the session itself rather than a copied transcript, and comes with a brief of where the work stands, what is waiting on a person, what the team asked for, and what happens next.
How to redirect an AI agent while it is running
Steering an AI agent means giving it new direction while a task is running, so its remaining plan changes without throwing away the steps already finished. Good steering shows the team which steps the direction changed, and when two people steer in opposite directions the agent stops and asks instead of trying to satisfy both.
Human-in-the-loop review for AI agents
Human-in-the-loop review for AI agents means an agent's result is a proposal until a person approves it. A useful review gate records who approved what, against which checks, and turns a rejection into the instruction for the next revision, so review is part of the work rather than a message sent somewhere else.
Running long AI agent tasks as a team
Long-running AI agents work on a single task for hours, days or longer instead of answering in one turn. Running one well takes three things a chat does not have: recovery from failures without a person pressing retry, a record anyone can rewind to see what happened, and a way for a teammate who was away to see what changed since they last looked.
Shared team memory for AI agents
Shared memory for AI agents is a store of what a team knows that every agent and teammate reads from, so the next session starts where the last one stopped. It is only useful if it can be trusted, which means knowing where each fact came from, catching facts that contradict each other, and letting facts that go out of date expire.
See how each kind of team uses a shared agent, or how a shared session compares with the alternatives.