Researchers described an interpretable machine-learning model intended for early detection of pediatric sepsis using routine lab inputs. By emphasizing explainability, the approach aims to make predictions more actionable for clinicians confronted with fast deterioration and limited specificity. On the platform side, Cenevo launched an AI-enabled inventory search capability for Mosaic, letting scientists query lab inventory using natural language while preserving traceability and governance. Together, the two developments reflect a parallel push toward both clinical decision support and lab workflow automation.