Results: Personalization of learning interventions using opinion leaders improves care but is expensive. Automated methods to deliver personalized learning interventions to physicians have not been widely studied or rigorously evaluated. We conducted this study to assess the impact of a computer-based personalized learning intervention for primary care physicians (PCPs) designed to improve control of glycated hemoglobin (A1c), blood pressure (BP) and LDL-Cholesterol (LDL) in adults with type 2 diabetes. The randomized trial was conducted from October 2006 to May 2007 in Minnesota. Eleven clinics with 40 consenting PCPs were randomized either to receive or not to receive a simulated personalized learning intervention designed to improve A1c, BP, and LDL in actual diabetes patients not at recommended clinical goals. Patients of intervention group PCPs had significantly better A1c (p=.044), SBP (p=.018), and DBP (p=.001), but not LDL relative to patients of PCPs randomized to the control arm of the study based on general linear mixed models with a repeated time measurement to control for clustering. Additional analytic models that adjusted for patient age, gender, and comorbidity showed similar results. Nearly all PCPs were very satisfied with the intervention, which most completed in less than 3 hours in split sessions over 1 to 2 days. An inexpensive simulated personalized physician learning intervention for primary care physicians significantly improved glucose and BP control in adults with type 2 diabetes who were not at recommended clinical goals.