Dive into a live coding session focused on constructing a cloud-native ML monitoring stack using open-source tools. Learn the fundamental principles of Machine Learning monitoring in production, then create a real-time web dashboard to measure model drift, feature statistics, and performance metrics. Explore how to integrate Python-based custom metrics into the dashboard. Follow along as Alon Gubkin, CTO of Aporia and experienced ML practitioner, guides you through the process of building a comprehensive monitoring solution for ML models in production. Gain hands-on experience in implementing essential monitoring techniques to ensure the reliability and performance of your machine learning models in real-world scenarios. Access the complete code on GitHub after the workshop to continue refining your ML monitoring skills.