Anthropic has an important message for Claude users: Starting August 14, auto mode will be the default ...
Anthropic has announced that its auto mode will become the default setting for its Claude Code platform starting August 14. This change will affect the Pro, Max and Team accounts. With this new change in place, the developers will no longer need to manually approve each actin that AI takes during programming tasks. Instead, Claude Code will automatically process unless an action is deemed ‘irreversible, destructive, or aimed outside your environment’. The company first introduced auto mode in March as a test feature designed to balance speed and control. In its latest announcement, Anthropic said testing showed auto mode to be safer than manual review — catching 89% of harmful actions compared to just 13.6% detected by human reviewers. The company noted that users tend to approve nearly all permission prompts manually, making automated oversight more effective.
The company first introduced auto mode in March as a test feature designed to balance speed and control. In its latest announcement, Anthropic said testing showed auto mode to be safer than manual review — catching 89% of harmful actions compared to just 13.6% detected by human reviewers. The company noted that users tend to approve nearly all permission prompts manually, making automated oversight more effective.
How the Claude auto mode works
Claude doesn't reach for your mouse and keyboard right away. It first checks whether a connector exists for the job—Slack, Google Calendar, and a handful of other services are already wired in. If a connector handles it, that's the path it takes. Only when there's no direct integration does it fall back to controlling your screen.
From there, it can open files, navigate a browser, type into forms, and click through menus—anything you'd do yourself. It always asks permission before touching a new application, and you can pull the plug at any point.
The feature pairs with Dispatch, Anthropic's task-assignment tool that lets you delegate work from your phone. The combination is what makes the whole thing more than a novelty. Assign a task on your commute, and the finished output is waiting on your desktop when you sit down. You can also set recurring tasks—scan my inbox every morning, pull the weekly metrics every Friday—and Claude handles them on schedule without being asked again.
How to get started with the auto mode in Claude
The feature is available for Pro and Max subscribers. You need the Claude desktop app installed and running on macOS. The mobile app alone won't control your computer—but you can use it to assign tasks through Dispatch, which then execute on your desktop in the background.
Claude creator Boris Cherny is also the fan of this feature
Claude Code Head Boris Cherny shared on social media platform X (formerly known as Twitter) that he and his team have been using auto mode exclusively for months, saying he “couldn’t imagine going back to permission prompts.” “The team and I use Auto mode exclusively, and have been for many months. I couldn't imagine going back to permission prompts! Really excited to get this out to everyone,” wrote Boris.
Anthropic added that new safety features — including prompt injection screening and customizable hard deny rules — have been integrated to prevent data leaks and unauthorized actions.
What it means for users
The update marks a significant step toward autonomous coding, reducing the need for human oversight while maintaining strong safety checks. For developers using Claude Code, the shift to auto mode is expected to streamline workflows and improve efficiency without compromising control.
The company first introduced auto mode in March as a test feature designed to balance speed and control. In its latest announcement, Anthropic said testing showed auto mode to be safer than manual review — catching 89% of harmful actions compared to just 13.6% detected by human reviewers. The company noted that users tend to approve nearly all permission prompts manually, making automated oversight more effective.
How the Claude auto mode works
Claude doesn't reach for your mouse and keyboard right away. It first checks whether a connector exists for the job—Slack, Google Calendar, and a handful of other services are already wired in. If a connector handles it, that's the path it takes. Only when there's no direct integration does it fall back to controlling your screen.
From there, it can open files, navigate a browser, type into forms, and click through menus—anything you'd do yourself. It always asks permission before touching a new application, and you can pull the plug at any point.
The feature pairs with Dispatch, Anthropic's task-assignment tool that lets you delegate work from your phone. The combination is what makes the whole thing more than a novelty. Assign a task on your commute, and the finished output is waiting on your desktop when you sit down. You can also set recurring tasks—scan my inbox every morning, pull the weekly metrics every Friday—and Claude handles them on schedule without being asked again.
How to get started with the auto mode in Claude
The feature is available for Pro and Max subscribers. You need the Claude desktop app installed and running on macOS. The mobile app alone won't control your computer—but you can use it to assign tasks through Dispatch, which then execute on your desktop in the background.
Claude creator Boris Cherny is also the fan of this feature
Anthropic added that new safety features — including prompt injection screening and customizable hard deny rules — have been integrated to prevent data leaks and unauthorized actions.
What it means for users
The update marks a significant step toward autonomous coding, reducing the need for human oversight while maintaining strong safety checks. For developers using Claude Code, the shift to auto mode is expected to streamline workflows and improve efficiency without compromising control.
Next Story