Anthropic to Default Claude Code's Auto Mode for Pro, Max, and Team Accounts

Aug 9, 2026

AI Summary

Starting August 14, Anthropic will make auto mode the default setting for its Claude Code service, reducing the need for human oversight. Testing has shown that auto mode is more effective at identifying harmful actions compared to manual review.

Anthropic will enable auto mode by default for Pro, Max, and Team accounts of Claude Code on August 14.
Auto mode allows the system to operate without requiring human approval for most actions, unless they are deemed irreversible, destructive, or outside the user's environment.
In testing with 1,053 paid testers, auto mode identified 89% of harmful actions, while manual review only caught 13.6%.
Claude Code Head Boris Cherny stated that the team has been using auto mode exclusively for months.
Anthropic has introduced additional safety features, including prompt injection screening and customizable hard deny rules to enhance security.

anthropicclaude codeprogrammingautomationai tools

Anthropic to Default Claude Code's Auto Mode for Pro, Max, and Team Accounts

Related Stories

OpenAI Releases ChatGPT Desktop Version for Linux Users

Automattic's Mesh CRM Launches on Android with Enhanced Features

Sandbar's Stream ring aims to revolutionize AI wearables with voice technology

DeepSeek Releases V4 Pro 0813 Model for Large-Scale Applications