| Setting | Change it when | What it does |
|---|---|---|
| Agent instructions | The agent should always work a certain way, in every room | Standing instructions the agent receives in every session. See Change what the agent is told. |
| Auto mode | The agent asks too often, but you still want risky actions checked | On by default. The agent’s provider decides which actions run without asking. See Let the agent act without asking. |
| Bypass permissions | The agent should never stop to ask | Off by default. Every action runs without asking, and it overrides Auto mode. See Let the agent act without asking. |
| Can manage agents | You want the agent to set up new agents for you | Lets the agent create agents on your machines. See Let the agent create agents. |
| Who can talk to your agent | Colleagues need to hand it work, or your other agents shouldn’t | Sets who may mention the agent, target it, or hand it work. See Choose who can instruct the agent. |
| Service access | The agent needs a service you’ve connected, such as Atlassian | Lets the agent’s sessions use your connection to that service. You can also add the agent on the service’s page, under Connectors. See Let the agent use your services. |
| Run in its own process | A managed agent shouldn’t share a process with the other agents on its machine | Gives the agent a process of its own, instead of running it inside its machine’s agent controller. See Keep the agent apart on its machine. |
| Advanced configuration | The agent needs a different model, or more or fewer tools | Model, tools, permission mode, and similar settings for the agent’s sessions. See Change the model or tools. |
| Provider sign-in | The agent’s sessions won’t start | Shows whether the agent’s provider is installed and signed in. Not on a managed agent’s page. See Check that the agent can start. |
| Name, Run location and Directory | The agent needs a new name, or has to run on another machine or in another directory | Fixed when the agent is created, except a managed agent’s Directory. See Rename or move the agent. |
Change what the agent is told
Edit Agent instructions on the agent’s page. The agent receives them in every session. Use them for what the agent should do in every room: its job, how it reports back, what to check before acting. Instructions for one room belong in that room’s room instructions instead. An agent Switch Console runs picks up a change at its next session. A managed agent’s running sessions finish what they’re doing, and its next session uses the change. Agent instructions are separate from the agent provider’s own instruction files, such asCLAUDE.md for Claude Code.
Let the agent act without asking
Under General, set Auto mode and Bypass permissions. Together they decide when the agent stops to ask before acting:
What Auto mode lets through depends on the agent’s provider:
- Claude Code and Codex check each action with their own automatic review.
- Antigravity runs file edits, and asks before commands and calls to connected services.
- Cursor asks before every action, the same as with Auto mode off.
Let the agent create agents
Under General, turn on Can manage agents. It’s also on the agent’s page in the Gateway. The agent can then see your machines and managed agents, and create agents on your machines on your behalf. Other people’s machines and agents stay hidden from it. Only the agent’s owner can turn it on, and it applies from the agent’s next request, without a restart. Don’t see Can manage agents? The server doesn’t run agent management. Ask whoever runs it to turn it on. Give each machine a description: in the Gateway, open Machines, edit the machine, and fill in Description. The agent reads it when choosing where a new agent should run. To ask for a new agent, see Ask an agent to create it. An agent created this way:- Belongs to you, not to the agent that created it.
- Answers only you and your other agents at first, including the one that created it. To permit more people, see Choose who can instruct the agent.
- Can’t create agents itself until you turn on Can manage agents for it.
- Runs on a managed machine. You don’t add machines yourself: Switch Console sets one up wherever it runs your agents, on this computer and on each remote host you’ve onboarded. A managed agent on this computer stops when you quit Switch Console, and one on a remote host keeps running.
Choose who can instruct the agent
Under General, pick an option from Who can talk to your agent. It decides who may mention the agent, target it, or hand it work:- Me and my agents (default): You and the agents you own, so one of your agents can hand work to this one. Not your colleagues, and not their agents.
- Only me: Only you. Not your colleagues, and not your other agents.
- Anyone: Anyone in the agent’s rooms. They don’t need a Switch account or a linked chat account.
- Custom rules: People, agents, and rooms you name individually.
Let the agent use your services
Turn a service on for the agent from the service’s page, or from the agent’s. In the sidebar, select Connectors, then the Discover tab, which lists every connector, such as Atlassian, Datadog, or Google Workspace. Select the service, connect it if needed, then add the agent. Or, on the agent’s page, select the plug icon and turn the service on there. You can turn services on for any agent you own.The administrator of your Switch server decides which connectors your server offers, and an admin decides which ones your workspace uses. Each connector’s card shows whether you can use it. The administrator of your Switch server can set up a connector marked Unavailable. GitHub also needs the server’s public address to be an
https address. A connector turned off for your workspace says so on its card, and an admin can turn it on.Connectors appear in the sidebar on servers that offer them. To get them on yours, ask the administrator of your Switch server.Keep the agent apart on its machine
Turn on Run in its own process. Only managed agents have it. Off, the agent runs inside its machine’s agent controller, alongside the other agents there. On, it gets a process of its own, apart from its neighbors.Change the model or tools
Expand Advanced configuration on the agent’s page. Every field is optional. Leave a field empty to keep its default.- Model and Effort choose the model and how hard it reasons. Model takes an alias, such as
sonnetoropus, or a full model ID. - Tools limits the agent to the tools you list. Disallowed tools removes tools from what it would otherwise have. Either way, the agent keeps its Switch tools.
- Permission mode, Max turns, Isolation, Persistent memory, Color, and Always run in background cover the rest.
.switch/config/<name>.json in its working directory. A managed agent’s are saved with the agent on the server.
For an agent Switch Console runs, these settings apply to every session Switch Console starts for the agent, including when someone addresses it in a room. If you start the agent yourself in a terminal instead, that session can still work in your rooms, but it doesn’t use these settings.
For an agent Switch Console runs, a change applies from the next session, and !reset isn’t enough. If the agent is already running:
- In Switch Console, open the agent’s session from the sidebar and select Stop.
- Address the agent in the room. That starts a new session.
- Continue in the new session. The stopped one stays open in the sidebar and looks the same.

