ChatGPT is learning to write like you, by reading your Gmail and Slack
OpenAI is testing a 'Writing Style' feature that studies your own messages and documents so the chatbot can mimic your voice. The privacy trade is real.
Key points
- OpenAI is testing a new ChatGPT feature called Writing Style that copies a user's tone by reading examples from connected apps.
- The tool pulls samples from three sources: Slack for messages, Google Drive and Notion for documents, and Gmail for email.
- OpenAI has confirmed the test to BleepingComputer but has not said when, or if, it will launch to everyone.
- Anthropic's Claude offers a similar feature called Styles, but users paste in samples themselves rather than granting access to live accounts.
- The design raises fresh questions about what a chatbot can see once you connect it to your personal inbox and workspace.
OpenAI is quietly testing a feature that lets ChatGPT write in your voice, by reading things you have already written elsewhere.
It is called Writing Style, and a small group of users can see it now. An onboarding screen tells them, "ChatGPT will write in your voice by referencing examples from your connected apps."
The idea is simple. Instead of pasting three old emails into a chat window every time you want ChatGPT to sound like you, the bot goes and finds those emails itself.
What is ChatGPT actually looking at?
It looks at writing you have produced inside apps you choose to connect. OpenAI groups the sources into three buckets: messaging, documents, and email.
Right now the connected apps on offer are Slack for chat, Google Drive and Notion for longer documents, and Gmail for email.
Once you switch it on, ChatGPT can pull real examples of how you write in each setting. That matters because most of us do not have one voice. You are chattier in Slack than in a board memo, and shorter in email than in a Notion doc.
| Category | Connected app |
|---|---|
| Messaging | Slack |
| Documents | Google Drive, Notion |
| Gmail |
How is this different from what Claude already does?
Anthropic, the company behind the rival chatbot Claude, has offered a similar tool called Styles for a while. With Styles, you paste or upload a few writing samples and Claude works out a template from them.
OpenAI's approach is bolder. Rather than asking you to hand over samples, it plugs directly into services where your writing already lives. That gives the model far more raw material to learn from, and a more honest picture of how your tone shifts between a Slack DM and a project brief.
It also means giving a chatbot standing access to your inbox and your work notes. That is a much bigger ask than dropping three paragraphs into a text box.
Should ordinary users be worried?
Not panicked, but thoughtful. This is authentication and authorisation working exactly as designed, which is the point worth pausing on.
When you "connect" Gmail or Slack to ChatGPT, you are using a protocol called OAuth, which is the standard way one app asks another for permission to see your data. You log in, you tick a consent box listing what ChatGPT can read, and a token gets stored. From then on, ChatGPT can reach into that account without asking again until you revoke it.
The security question is not whether OAuth is safe. It is well understood, and defined in RFC 6749. The question is what scopes, meaning the specific permissions ChatGPT requests, and whether the average user reads the consent screen before clicking Allow. Most people do not.
Multi-factor authentication, the extra code from an app or text after your password, would not change any of this. You granted the access on purpose. That is the awkward part of the modern AI stack: the biggest risk is often a permission you agreed to when you were half paying attention.
What should you actually do?
A few sensible habits, if you try Writing Style or anything like it.
Read the consent screen. If ChatGPT is asking to read all mail rather than just drafts, notice that. Check your Google account's connected apps list every few months and remove anything you no longer use. And keep work and personal accounts separate, so a personal experiment does not quietly hand a chatbot your employer's data.
OpenAI has confirmed the test but has not said when Writing Style will roll out widely, or whether the connector list will grow.
