OpenAI Dots permissions: what your Dot can access

Short answer

Give it one app for one job. Use action rules to decide what it can do on its own, and what needs your say-so. Want a clean slate? Reset the Dot; disconnecting one app only stops future access.

How action rules work

Think of Custom rules as four lanes: go ahead, do the thing I already approved, ask me first, or hand it back. “Pre-approved” means you named that action in your prompt. The lane markers help; you’re still driving the policy. OpenAI Help Center

What happens between chats

A Dot can check connected apps and save memories between chats. Handy for recurring work; a good reason to keep an eye on Activity. Need quiet? Pause is its clock-out button.

Connecting your computer

Computer access starts off. To switch it on, open the desktop app on that computer and choose Allow access. The Dot can then reach files through its messaging channels. Revoke permission in the app when you’re done. Its cloud computer is separate from yours.

Approvals and the pause control

Choose which actions need a “hey, are you sure?” first. You can pause from the profile menu and resume later. Pause stops ongoing work; it does not erase connected-app data or reset the Dot.

What happens when you disconnect an app

Disconnect stops future access, not past collection. To delete saved conversations, memories, and scheduled tasks, reset the Dot.

Reset: what gets deleted

Reset deletes the Dot’s conversations, memories, and scheduled tasks. Read the deletion notice before confirming; after reset, you start a new ChatGPT chat.

Memory and model training

Dots can use shared ChatGPT memory and keep Dot-specific memories. Model-training choices depend on your account: personal users can manage them in Data controls, while managed workspaces have separate terms and admin settings. Connected-app information can have additional conditions; check the app’s permissions and OpenAI’s data controls before connecting sensitive accounts.

Before you connect an app

Connect an app to solve a specific chore, not just to see what happens. Check what it can expose and which actions need your approval. Start with one; expand only when there is a reason.

FAQ