OpenAI's ChatGPT Work Agent Can Now Access Password-Protected Sites
ChatGPT Work agents can now reach login-gated websites via a human takeover step, with sessions that persist across runs
- New: ChatGPT Work agents can now operate on login-gated websites via a manual browser takeover step.
- How it works: The agent pauses, you log in manually in the virtual browser, then return control -- the agent continues the task.
- Session persistence: Cookies persist across sessions, so you only need to sign in once per site.
- Privacy: Screenshots are disabled during takeover; OpenAI never sees your password.
- Not the cloud browser: The cloud browser still cannot sign in to any site at launch -- this feature is exclusive to agent mode's virtual browser.
- Availability: Agent mode is on Pro, Plus, Business, Enterprise, and Edu plans; login takeover steps don't count against message limits.
OpenAI's ChatGPT Work agent can now operate on websites that require a login. The agent doesn't handle authentication itself. You sign in manually, then hand control back.
How the handoff works
When the agent hits a page requiring authentication, it pauses and prompts you to take over the virtual browser via ... → Take over browser. You log in yourself. During that window, the agent captures no screenshots, so passwords and sensitive inputs stay private. Once you return control, the agent resumes from its prior workflow state, though in some cases it may need to restart the run or prompt you again if the handoff can't complete cleanly.
Cookies persist across sessions, so you authenticate once and subsequent runs on that site pick up without repeating the login. To clear saved sessions, sign out of the relevant sites and remove cookies in your ChatGPT data control settings.