Anthropic Enables Auto Mode For Claude Code
Anthropic PBC announced on March 24, 2026 that it is launching "auto mode" for Claude Code, allowing the coding assistant to autonomously decide permissions for file writes and bash commands. The research-preview feature applies internal safety classifiers to approve or block each action and checks for prompt-injection attacks, and will initially roll out to Enterprise and API users on Claude Sonnet 4.6 and Opus 4.6. Anthropic recommends using auto mode only in sandboxed environments to limit potential damage.
Key Points
- 1Makes Claude Code autonomously approve or block file writes and bash commands via auto mode.
- 2Adds per-action safety classifiers and prompt-injection detection to balance speed with operational safety.
- 3Enables faster unattended coding workflows but requires sandboxed deployment due to opaque guardrail behavior.
Scoring Rationale
Strong practical impact and official rollout, but limited novelty and opaque safety guardrails reduce confidence.
Sources
Public references used for this report.
View 1 more source
Practice with real Logistics & Shipping data
90 SQL & Python problems · 15 industry datasets
250 free problems · No credit card
See all Logistics & Shipping problems
