Mastitis detection has advanced rapidly, with new technology promising better outcomes. In this episode, we explore mastitis as a systems-level problem shaped by housing, labor, management decisions, and data interpretation, not just pathogens. Dr. Justin Hess, a bovine veterinarian in Michigan, and Dr. Alon Arazi, chief veterinarian at Afimilk, discuss with me where current detection tools perform well, there they fall short, and why subclinical mastitis remains one of the biggest blind spots on dairies. We discuss how automated monitoring systems flag abnormal patterns, why they are not a diagnostic on their own, and how false positives can undermine trust if sensitivity and specificity are poorly balanced. The conversation also looks ahead to the future of mastitis detection, including earlier risk identification, predictive modeling, and the potential for insight into pathogen type.