via TechCrunch AI
Anthropic Makes Claude Code's Auto Mode the Default
Programming with Claude Code is about to become even more hands-off. Anthropic has announced that auto mode will become the default setting for Pro, Max, and Team accounts starting August 14, 2026, reducing the need for human oversight during coding sessions.
First introduced as a test version in March 2026, auto mode was designed to strike a balance between speed and user control, according to the company's announcement on Friday. In this mode, Claude Code will no longer pause to ask for approval at each step. Instead, it will proceed automatically unless an action is deemed 'irreversible, destructive, or aimed outside your environment.'
Anthropic claims that testing has shown auto mode to be safer than manual review. In a study involving 1,053 paid testers, auto mode detected 89% of harmful actions, whereas human review caught only 13.6%. The company attributes this disparity to the tendency for manual review to become routine, noting that users approve 97% of permission prompts in Claude Code.
Boris Cherny, head of Claude Code, expressed his enthusiasm on X, stating, 'The team and I use Auto mode exclusively, and have been for many months. I couldn’t imagine going back to permission prompts!'
To address safety concerns, Anthropic has also rolled out new features, including prompt injection screening and customizable hard deny rules, aimed at preventing issues like data exfiltration. These additions are part of a broader effort to ensure that reduced oversight does not compromise security.