Agents And SkillsAgent Skill

Claude Code auto mode (classifier-based approvals)

March 25, 2026Anthropic, cat

Anthropic and cat describe Claude Code auto mode as a safer autonomy middle-ground where classifiers decide when to request approval, improving UX while balancing safety for daily-driver use.

How we designed Claude Code auto mode.
Auto mode is a safer middle ground: we built and tested classifiers that make approval decisions instead.
Auto mode is a step change improvement in the Claude Code UX, balancing autonomy and safety.
Now available to Claude for Team users! `claude --enable-auto-mode` to turn on
Many Claude Code users let Claude work without permission prompts.
Now available to Claude for Team users! `claude --enable-auto-mode` to turn on, then Shift + Tab to enter the mode
“Many Claude Code users let Claude work without permission prompts.”
“Auto mode is a safer middle ground”
“we built and tested classifiers that make approval decisions instead.”
Anthropic
cat
safetyapprovalsuxclaudeanthropicclaude codeagentic

See what experts are saying right now

This finding is one of many signals tracked across Artificial Intelligence. The live feed updates every few hours with new expert voices, debates, and emerging ideas.

← Back to Artificial Intelligence