To evaluate the impact of a continuing medical education program on family doctors to improve prescription of hypoglycemic drugs. An observational study was conducted with two groups of comparison (with-without program) and before-after periods. The unit of analysis was the visit. The period of evaluation comprised six months before and six after implementing the program. The outcome variable was the appropriateness of prescription that was based upon two criteria: appropriate selection and proper indication of the drug. Logistic regression models and the double differences technique were used to analyze the information. Models were adjusted by independent variables related with the patient, the visit and the PCC, the more relevant ones were: sex, obesity, conditions other than diabetes, number of visits in the analyzed period, number of drugs prescribed, size of the PCC and period. the program increases 0.6% the probability of appropriate prescription and 11% the probability of appropriate choice of the hypoglycemic drug in obese patients.