Would you let AI handle your emails?
If the masochist in you says “yes,” well, I guess you’re now in luck!
Anthropic has just updated its Claude connector for Google Workspace to allow full Gmail inbox management. This notably includes the ability for the AI assistant to send and reply to emails without additional user input or approval.
This Tweet is currently unavailable. It might be loading or has been removed.
Claude Connectors are integrations that connect Anthropic’s AI assistant Claude to external apps. As 9to5Google points out, a Claude Connector for Google Workspace has already existed for a while. Along with Google Calendar and Google Drive, this Claude Connector included some access to Gmail.
Mashable Light Speed
However, this week, Anthropic added a new capability to the connector: Claude can now send and reply to emails without even checking with the user. Claude can also forward emails now without asking for approval too.
Claude still needs a human user to ask the AI assistant to draft or reply to an email. But, once Claude writes up the response, it no longer needs to check with the user before sending it.
According to Anthropic, users can still control when Claude checks for approval before sending an email. Anthropic also says Claude asks for approval by default. So, Claude users need to change their settings to give the AI permission to hit “send’ without asking first.
One caveat for free Claude users: If you’d like Claude to send emails on your behalf, you will need to subscribe to a paid Claude plan.
