Announcing public preview: Phishing triage agent in Microsoft Defender

Microsoft announces the Public Preview of the Phishing Triage Agent in Microsoft Defender—an LLM-powered capability that autonomously analyzes user-reported phishing emails, provides explainable verdicts and decision maps, learns from analyst feedback, and integrates with Automated Investigation and Response to speed remediation. Designed to reduce SOC workload by auto-resolving most false positives and improving mean time to triage, it operates under least-privilege, Responsible AI, and Zero Trust principles, offering dashboards for performance visibility and administrative controls for oversight.