The study tested the ePOCT+ digital algorithm to support physician decision-making in prescribing antibiotics for children under 14 years of age in 32 Rwandan health centers in pediatric outpatient care. The pragmatic cluster non-randomized controlled trial included 47,822 new consultations from December 2021 to April 2023, with 16 centers using ePOCT+ and 16 providing standard care. Antibiotic prescribing decreased from 70.5% to 24.5% in the intervention-control comparison (absolute difference −46.0%, 95% CI [−52.5, −39.5]) and to 27.5% in the pre-post comparison (absolute difference −43.0%). The rate of clinical failure was not worse (aRR 1.07, 95% CI [0.97, 1.18] in intervention-control). ePOCT+ improved malaria testing in febrile children (aRR 1.27, 95% CI [1.08, 1.41]) and increased referrals for hospitalization. Prescribing remained low (25–40%) during the 10-month long-term evaluation. The authors recommend integration into Rwanda's national electronic health record platform. The study is registered at Clinicaltrials.gov NCT05108831.