Machine learning systems in production need to need systems support to manage their data (features, models) and their compute (training, inference). In this talk, we show you how to build an end-to-end ML system that predicts wave heights at a beach. The system is written in only Python.. It is hosted on free serverless services - Github Actions (compute) and Hopsworks (features, models). It is a continually improving ML system that keeps collecting more data, making better predictions.