Claude's apps will stop asking you to approve every step starting next week, with an automatic safety check taking over.

On Thursday, Oct 22, Anthropic said sessions in the Claude web, desktop and mobile apps will run in "auto mode" by default starting next week on the Pro, Max and Team plans (Claude on X).

Right now, when Claude wants to take an action, such as running a command or using a tool, it can stop and ask you to approve it. In auto mode, an automated check reviews each action instead: safe actions go ahead, and risky ones are blocked while Claude looks for another way to do the job (Anthropic). You can switch back to manual approval at any time. Anthropic says the change applies to new sessions in "most" Claude apps, and Enterprise admins will get an email before it becomes the default for their organizations.

The announcement doesn't mention the Free plan. Auto mode has already been the default in Claude Code, Anthropic's coding tool, since Aug 14. In a study Anthropic ran for Claude Code with 1,053 paid testers, people caught a planted dangerous command 13.6% of the time, while auto mode blocked 89% of them.

Anthropic notes those figures are for Claude Code, and it still recommends checking Claude's actions yourself for high-stakes changes, because the classifier "does not eliminate risk."

When you'll feel it: sometime next week, new chats that use tools will stop pausing for your OK on each step. If you'd rather keep approving actions yourself, switch back to manual once the change reaches your account.