Assign tasks to Claude from anywhere in Cowork

Cowork now gives you one continuous conversation with Claude that you can reach from your phone or your desktop. Assign Claude a task, go do something else, and come back to the finished work. Claude runs on your computer—with access to your local files, connectors, and plugins—and messages you the result when it's done.

Requirements

To use this capability, you need:

How it works

Instead of starting a new session for each task, you have a single persistent thread with Claude. This thread doesn't reset—Claude retains context from previous tasks, so you can pick up where you left off.

Message Claude from your phone on the way to work, then follow up from your desktop when you sit down. It's the same conversation, same context, wherever you reach it.

When you assign a task, Claude works on your desktop computer using the files, connectors, and plugins you've already set up in Cowork. Claude messages you the outcome—a spreadsheet, a memo, a comparison table—rather than showing you every step of the process.

Get started

Follow these steps to get started:

After completing these steps, your continuous conversation with Claude syncs across both surfaces automatically.

What you can do

From your phone, you can hand Claude tasks that use everything on your desktop, including things you can't open on your phone. For example:

Claude uses the same connectors, plugins, and file access you've already configured in Cowork. You don't need to set anything up separately for mobile.

Retrieve files and outputs

When Claude finishes a task that produces a file, you can access it directly from mobile or find it on your desktop at the location Claude specifies.

Safety considerations

From your phone, you can now access everything on your desktop through Claude—including files, connectors, and any plugins you've installed. Be mindful of what access you've granted Claude in Cowork, since this capability extends that access to a mobile surface.

Giving a mobile AI agent remote control of a desktop AI agent creates a chain where instructions from your phone can trigger real actions on your computer—including reading, moving, or deleting local files, interacting with connected services, and controlling your browser. This is powerful, but it also means mistakes (or malicious content the model encounters along the way) can have real consequences. A manipulated instruction, an unexpected command, or a phishing link opened in your browser could cascade into actions that are difficult or impossible to undo.

Before enabling this, make sure you:

Only connect these agents if you're comfortable with what they could do, not just what you intend them to do.

Current limitations

This is a research preview with the following limitations: