Response to antidepressants (ADs) is highly variable and partly genetically driven, but the utility of pharmacogenetic testing in guiding ADs treatment is still controversial. We conducted a retrospective, naturalistic study to explore the utility of CYP2C6 and CYP2C19 genotyping in ADs treatment in a sample of 156 patients diagnosed with major depressive disorder from south Sardinia (Italy). Clinical data, including history of medication regimens, adverse reactions, and response to ADs were collected over the last five years preceding recruitment. Patients received pharmacogenetic testing at recruitment and were classified depending on whether their history of treatment regimen followed the recommendations of the Clinical Pharmacogenetics Implementation Consortium (CPIC)). Non-responders to ADs had a larger number of therapeutic regimens and of medication changes due to lack of response compared to responders. Patients with at least one incongruent regimen had a larger number of total therapeutic changes and fewer congruent regimens. Metabolizing phenotypes of CYP2D6 were not associated with response to ADs or changes in regimen of any kind. However, the group of ultra-rapid metabolizers for CYP2C19 showed significantly smaller improvement in symptoms while the poor-metabolizers showed a larger number of medication changes for side effects compared to normal, intermediate and rapid metabolizers. Our findings suggest that the implementation of pharmacogenetic testing based on CYP2C19 could be clinically useful in guiding AD treatment, but further studies are warranted to investigate the clinical implications of implementing PGx testing in depression.