Every time you use the AI features, we start by finding the most relevant parts of your code locally (~10-300 lines of code).

We then beam this chunk of code up to our (Cursor’s) servers and input it into a prompt that is sent to an OpenAI model.

By default, we (Cursor) persist this prompt on our server to improve Cursor. To turn this off, you can enable Privacy Mode.

To enable Local Mode, open the Cursor Settings Popup, navigate to the Privacy Mode section, and set it to enabled.