Skip to content
ClaudeClaude

How auto mode works with Claude Code

Auto mode lets Claude Code complete long-running work with fewer interruptions, with a separate classifier screening each action instead of you. This video covers how the classifier works, why Claude never approves its own actions, and how to configure auto mode for your environment and team. Read the announcement → https://www.anthropic.com/engineering/claude-code-auto-mode Read the docs → https://code.claude.com/docs/en/auto-mode-config 0:00 Intro 0:44 How auto mode works 3:33 Configuring auto mode 4:49 Outro

Aug 4, 20265mWatch on YouTube ↗

At a glance

WHAT IT’S REALLY ABOUT

Claude Code auto mode uses classifiers, probes, configurable trust boundaries

  1. Auto mode reduces “approval fatigue” by allowing Claude Code to proceed with fewer permission prompts while still screening for harmful actions.
  2. Instead of Claude approving its own work, a separate classifier evaluates proposed actions using only the user’s messages and tool-call data, not Claude’s reasoning or tool outputs.
  3. A server-side probe scans tool results (like web pages or file contents) for prompt-injection attempts before that content enters Claude’s context, creating a second defense layer.
  4. A tiering system sends only higher-risk, harder-to-undo actions (e.g., shell commands, web fetches, external operations) to the classifier, while many read-only/recoverable actions bypass it.
  5. Admins and developers can configure the trust boundary (internal vs external resources) and rules (allow/ask/deny, soft vs hard guidance) to match organizational infrastructure and risk tolerance.

IDEAS WORTH REMEMBERING

5 ideas

Auto mode shifts review from humans to an independent safety check, not to Claude itself.

Actions are screened by a separate classifier to avoid “self-review” bias; it inspects user intent via messages/tool-call data while ignoring Claude’s reasoning and tool outputs.

Safety is enforced through two complementary layers: probe then classifier.

Tool outputs are scanned server-side for hidden instructions (prompt injection) before entering context, and the classifier then verifies subsequent actions still match the user’s intent.

Only higher-risk actions are classifier-gated; many routine actions are not.

Read-only or recoverable operations like searching a repo or editing project files usually bypass the classifier, while shell commands, web fetches, and external-reaching actions are escalated.

Default “internal” boundaries are narrow, so configuration is essential for real organizations.

By default, only the working directory and Git remotes count as internal; without adding your company infrastructure, many normal actions will be treated as external and scrutinized or denied.

Environment text and soft/hard guidance shape classifier decisions, but rule types differ in enforceability.

Environment/allow/soft deny/hard deny fields guide classifier judgment, while explicit deny rules and ask rules are the hard mechanisms to block or force prompts even in auto mode.

WORDS WORTH SAVING

5 quotes

In our research, 97% of permission prompts in Claude Code get approved.

Unknown

Auto mode checks for potentially harmful actions while letting Claude complete long-running work with fewer interruptions.

Unknown

It would be easy to assume Claude is now approving its own actions, but that would make Claude its own reviewer, introducing bias through shared context.

Unknown

We tested this by running prompt injection attacks against Claude Code. With probes and auto mode enabled, the attack success rate in our evaluations dropped to zero.

Unknown

When you are rolling it out, start narrow. Watch what gets denied, and then widen it from there.

Unknown

Permission prompts and approval fatigueAuto mode safety modelSeparate classifier review mechanismPrompt-injection probing of tool resultsTiering of actions by reversibility/riskConfiguring environment trust boundariesAllow/ask/deny rules and rollout strategy

High quality AI-generated summary created from speaker-labeled transcript.

Get more out of YouTube videos.

High quality summaries for YouTube videos. Accurate transcripts to search & find moments. Powered by ChatGPT & Claude AI.