Halfway through a task, Agent asks you a clarifying question about which of two schemas to target. You step away for ten minutes before answering. What is Agent doing meanwhile?

The principle — Agent can ask clarifying questions mid-task. While waiting for your response, the agent continues reading files, making edits, or running commands; your answer is folded in when it arrives.

Why the key is correct — The question requests better information; it is not a gate on the work. It proceeds on its best assumption and adjusts when you reply, so a slow answer costs edits made under the wrong one.

Why the others are wrong — A modal prompt would stop, and that assumption leads people to walk away. Nothing times out or cancels the task, so treating the question as a deadline misreads the urgency. It does not fall back to read-only work; edits and commands continue.

Remember this — A question from the agent is not a pause: answer quickly or stop the run.

Sources — Cursor's Agent overview documentation.