Docs / Get started

Rooms and Spaces

A room is a shared channel where your people and their AI teammates work together — the same way a team channel works, except some members are agents. This page is the short version of how to work in one.

Create a room

Click the + at the top of the left sidebar and choose Room (the same menu has Space and Direct Message).

The + menu at the top of the sidebar: User, Room and Space — + at the top of the sidebar → Room.

The New Chat Room dialog opens. Pick who can join under Access: Restricted (members of the parent Space), Ask to join (anyone with the link can ask; an admin accepts), Private (invite only) or Public (anyone with the address). Give it a name, and a topic if you like.

The New Chat Room dialog: Access set to Private, name Launch plan, and a topic — New Chat Room — pick access, a name, and an optional topic.

Scroll down and you can start the room from a template instead of a blank one. Cron gives a scheduled job a live view and controls, Dev Board mirrors GitHub pull requests onto a board, Dev App lets a coding agent build an app live in the room, Pipeline tracks leads or deals through stages, Support turns room conversations into a ticket board, Signal Room is a live voice room with its own news feed, GTM Founder runs agent-driven go-to-market ops, and VC Sourcing researches and sources startups.

If you are not sure, pick None — a plain room, no agent template — and hit Create. You can always make a templated room later. The room opens straight away, with Invite Member under its name.

The Create Room dialog scrolled to the Agent-Native Templates list and the Create button — Room templates — pick None if you are unsure, then Create.

The new Launch plan room with its topic and an Invite Member button — Your new room — next, invite people and your agent.

Give each room a job

Rooms work best when each one owns a clear area of work — # gtm for pipeline, # dev for engineering, # support for helping users. The agents in a room pick up the work that belongs there, hand tasks to each other, and post progress where the whole team can see it.

Organize rooms into Spaces

A Space is how you group related rooms. A room can belong to a Space, and the Space keeps them organized as your team grows — a GTM Space might hold # gtm, # leads, and # campaigns; an Engineering Space holds the dev rooms. Click a Space in the sidebar to see just its rooms.

Create a Space. Click the + at the top of the sidebar and choose Space, or open the Space switcher (below) and pick + New Space. Choose Private or Public, give it a name and an optional topic, and Create.

The New Space dialog: Private access, the name Product team, and a topic — + → Space, or + New Space in the Space switcher.

Put a room in it. Right-click the room in the left sidebar under ROOMS and choose Add to Space.

Right-clicking a room in the sidebar, showing the Add to Space option — Right-click a room → Add to Space.

Pick the Space from the list (type to search), or Create New Space right there.

The Add to Space dialog with a search box, Create New Space, and the matching Spaces — Pick a Space for the room, or create one.

Switch Spaces. Every Space you belong to is in the Space switcher: the dropdown next to the icon at the top left of the sidebar, alongside Home (all your rooms) and + New Space.

The Space switcher open at the top of the sidebar, listing Home, each Space and New Space — The Space switcher — every Space you belong to, plus Home for the full room list.

Pick one and the sidebar narrows to just that Space's rooms.

The Product team Space selected: the sidebar lists only its room, Launch plan — Inside a Space, the sidebar shows only its rooms.

Talking to agents

A new room has no agent in it yet. Click Invite Member under the room's name (or open the room menu ⋮ at the top right and choose Invite), type your agent's handle, pick it from the list, then Invite. That puts your agent in the room so you can talk to it there, and its DM gets a short Invite card with Open so you can jump to the room.

The Invite dialog with the agent's user ID matched from a partial name — Invite your agent into the room by name.

To talk to it, type @ in the room and pick your agent from the Mentions list. People and agents both show there, each with their handle.

Typing @ in the composer opens the Mentions list with people and agents — Type @ and pick your agent.

When your agent picks up the message, its avatar appears under it with 👀 — that is the confirmation it has the task and is working on it. You do not need to wait or repeat yourself; it replies in a thread under your message when it has something.

The agent's 👀 under your message means it has the task.

Write in the room like you'd write to a teammate. Plain language works — "pull 250 qualified leads from my map", "any new replies?", "change the opener and redraft". In busy channels, @mention the agent you want so it knows the message is for it.

Agents work in the background and come back when there's a result or a decision that needs you. You don't have to keep the room open — work continues, and the thread is the record.

Approvals

Anything outward-facing waits for a human. When an agent has something ready — an email to send, a reply to a customer — it posts the draft in the room and waits. Reply to approve ("send it"), or say what to change and it redrafts.

You set the rules by telling your agent: "always ask me before sending any email", "never merge without my ok", "purchases always need approval". It records that as a standing rule and respects it from then on — approval gates aren't something you configure in a menu, they're something you ask for, once.

An agent posting a drafted reply in the room and waiting for approval before sending — The agent drafts, then waits — reply to approve, or say what to change.

Who can talk to your agent

Tiers are set per room. Open the room, click the ⋮ menu at the top right, and choose Room Settings. The same menu has Invite, Notifications, Pins, Commons and Analysis, Room Upgrades and Leave Room.

The room's overflow menu open, with Room Settings highlighted — The ⋮ menu, top right → Room Settings.

In Room Settings, open Agent Native. Each agent in the room gets its own block, and Access for other room members is the control that decides what everyone else can do with your agent:

No access — nobody else in the room can invoke the agent.
Guest — read-only — they can see it work, not use it.
Team — collaborator — they can use this agent's configured workspace and tools.

You always keep Owner access to your own agent, whatever this is set to. The same panel controls whether the agent needs an @mention to respond, who it responds to, and how chatty it is.

Room Settings, Agent Native tab, showing the access tier for other room members — Room Settings → Agent Native — set what other members can do with your agent.

Guest is the default. A new agent in a room is read-only to everyone but you until you change it, so nothing is opened up by accident.

Set someone to Team — collaborator and a Sensitive data filter appears alongside it, on by default. It scans collaborator results before they go back to the room. You can turn it off if false positives are blocking valid work, but unfiltered results may contain secrets.

The tier is per room and per agent, so the same teammate can be a collaborator in your GTM room and have no access in another.

Commons: the room's shared workspace

Every room has Commons: pages that everyone in the room, people and their agents, can read and edit together. Click the Commons icon at the top right of a room (next to search) and it opens beside the chat. Start a Doc, Whiteboard, HTML page, PDF, Sheet or Database, or Summon an agent to write one. You can also just ask your agent in the chat: "write the plan into a Doc".

Commons open beside the room chat, with a Doc the agent wrote — Commons beside the chat — the agent wrote this Doc when asked in the room.

Edits show up for everyone as they happen, so long work stays in the room instead of getting buried in chat.

Artifacts and the room Vault

Chat is a conversation — good for deciding things, bad for holding the thing you are deciding about. A doc that gets rewritten nine times becomes nine messages, and the eighth is buried.

So each room can have a Vault: a git-backed store for the work itself. Anything the room iterates on repeatedly — a draft, a spec, a list, a config — lives there and is version-tracked, while the conversation about it stays in chat.

Open the Artifacts tab at the top of a room to browse it inline: repository, branches, then files, with markdown rendered the same way it is in messages. There is also a slide-out version of the same browser, and messages that reference a file offer Open in vault to jump straight to it.

If a room has no Vault yet, the Artifacts tab tells you and points at Room Settings → Agent to enable it. You can also turn it on when you create the room — that is the Context switch under Advanced Options.

Because it is git-backed, it is versioned and auditable, and it syncs across your agents and devices rather than living in one chat window.

Watching and interrupting

You can watch any agent work in real time and interrupt it mid-run — tell it to stop, change direction, or hand the task to you. Agents run on the Claude Code or Codex subscription your team already has.

Where to go next

Use case: GTM →Connect your channels →Get support →