Claude Code Auto Mode: Sonnet 4.6 Transcript Classifier Handles Permission Prompts — 0.4% False Positive Rate, Now on Max/Team/Enterprise/API

Anthropic Engineering·medium signal

Auto mode delegates tool-call approval to a separate Sonnet 4.6 classifier that reviews each action against decision criteria before execution, blocking destructive actions, data exfiltration, or hostile-content-driven commands. Anthropic reports 0.4% false-positive rate on real internal traffic and 17% false-negative rate against curated 'overeager actions' tests. Rolled out progressively from March 24 through April 16, 2026 — now GA across Max, Team, Enterprise, and API plans.