Modern software systems and products increasingly rely on ML models to make data-driven decisions based on interactions with users and systems. For broader adoption, this practice must accommodate SW engineers without ML background and provide mechanisms to optimize for product goals. In this work, we describe an end-to-end ML platform, which offers easy-to-use API for decision-making and feedback collection. It supports the full end-to-end ML lifecycle from data collection to model training, deployment, inference, and extends to evaluation and training against product goals. We outline the platform architecture and overall impact of production deployment. We also describe the learning curve and summarize experience from platform adopters.