About 250 million children under age five are at risk of not reaching their developmental potential due to continued exposure to ill health, malnutrition and lack of appropriate learning environments. A large number of initiatives have been launched in recent years to support early childhood development, with home visiting programs increasingly being recognized as a key strategy for improving child wellbeing. However, the most effective ways to reach families in low income settings remain unclear due to the large expense associated with personal family visits. This project assesses the effectiveness and equity of a newly developed digital platform designed to deliver evidence-based, individualized parenting support through automated services. The Afinidata platform uses state-of-the art machine learning algorithms to allow caregivers to get answers to questions about child health and development, while also identifying and promoting age- and development-appropriate activities for parents to support their children. The goal of this study is to rigorously assess the reach, impact and cost effectiveness of this digital platform in a poor rural population through a randomized controlled trial. The study is designed as mixed-methods evaluation approach with repeated feedback into the Afinidata system. A total of 2400 newborns will be enrolled in a randomized controlled trial in San Marcos, Peru, and followed up for two years. The primary study outcome will be children's healthy development at 24 months of age assessed through the Bayley Scales of Infant and Toddler Development (BSID-III). Secondary outcomes will be systems utilization, program coverage and cost-effectiveness, as well as caregiver satisfaction. If proven effective, this innovative digital platform may increase global access to low-cost parental support -a widely recognized key strategy for improving child well-being.