Claude Code to default-enable Auto Mode on August 14 for longer autonomous tasks with risk interception
On August 7, Anthropic announced Claude Code will default-enable Auto Mode starting August 14 for Pro, Max, and Team plans. A classifier evaluates each tool call in real time to intercept destructive or out-of-scope actions.
On August 7, Anthropic announced that Claude Code will default-enable Auto Mode starting August 14 for Pro, Max, and Team plans to support longer autonomous task runs. Previously, users had to confirm each tool call manually; Auto Mode uses a classifier to evaluate each call in real time and intercept potentially irreversible, destructive, or out-of-scope actions.
Anthropic said internal testing, third-party security reviews, and real-world usage data show Auto Mode is safer than traditional manual review. Enterprise teams including Adobe, Nuro, and Gusto have already deployed Auto Mode in production. Anthropic noted Auto Mode remains optional for Claude Enterprise and Claude API customers, with broader default rollout planned over the coming months.