# OpenAI's always-on dots agents can now read sign-in codes from a user's inbox and log in to websites

The permission-gated feature lets agents running in OpenAI's cloud browser complete email verification, a step that websites treat as proof that a human controls the account.

- Published: 2026-11-08T06:30:20.452Z
- Canonical: https://polylog.news/ai/2026-11-08/openai-s-always-on-dots-agents-can-now-read-sign-in-codes-fr
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Polylog editors](https://polylog.news), [Crypto Briefing](https://cryptobriefing.com/openai-dots-agents-2fa-email-codes/), [BetaNews](https://betanews.com/article/openai-dots-agents-chatgpt/)

OpenAI's dots, the ChatGPT agents that keep working in their own cloud browser after a user logs off, can now use the one-time sign-in codes that websites send to a connected inbox. When a sign-up or login flow sends a code by email, a dot…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-11-08/openai-s-always-on-dots-agents-can-now-read-sign-in-codes-fr (subscription information: https://polylog.news/pricing).