Anthropic will make Claude Code auto mode the default for Pro, Max, and Team

Anthropic will turn on auto mode by default for Claude Code Pro, Max, and Team accounts starting on August 14, TechCrunch reported, citing the company's announcement. In auto mode, Claude Code continues without asking for human approval at each step unless an action is judged irreversible, destructive, or aimed outside the user's environment. Anthropic first tested the mode in March as a balance of speed and control. In a study with 1,053 paid testers, Anthropic said auto mode caught 89% of harmful actions versus 13.6% for human review, and that users approve 97% of permission prompts in manual review. The company said it has also added prompt-injection screening and customizable hard deny rules meant to block steps such as data exfiltration.