Auto mode becomes the default in Claude’s web, desktop and mobile apps on Pro, Max and Team plans

Anthropic announced on October 22, via the @claudeai account, that starting next week sessions across Claude’s web, desktop and mobile apps will run in auto mode by default on Pro, Max and Team plans. Instead of asking for approval at each step, an automated check reviews actions: safe ones go ahead, risky ones are blocked while Claude looks for another route. Users can switch back to manual anytime.

An October 22 update to the company’s blog post says the change applies to new sessions “in most Claude apps.” Enterprise admins will get an email before the switch. Auto mode has been the default in Claude Code on Pro, Max and Team plans since August 14. There, each tool call goes through a separate classifier that targets irreversible, destructive or outward-facing actions. After three blocks in a row, or twenty in a session, it falls back to manual approvals.

Anthropic notes that the data in the post is specific to Claude Code. In a controlled study with 1,053 paid testers, humans caught a dangerous command slipped into a session 13.6% of the time, while auto mode blocked 89% of the same commands. On a synthetic attack set from Apollo Research, the classifier’s miss rate fell from 12% to 7% after hardening. The company says that figure isn’t the miss rate on real traffic. All numbers are Anthropic’s own.