Introduction to the fundamentals of causal inference, an emerging field in machine learning that goes beyond correlational patterns to improve decision-making. Causal inference methods rely on patterns generated by stable and robust causal mechanisms and promises to address fundamental challenges in machine learning such as generalizability, interpretability, and bias. Cause and effect can be captured in a formal graphical model (causal graph) and answered systematically using available data. The DoWhy Python library implements a four-step causal modeling framework for analyzing decision-making tasks. Featuring Emre Kiciman, Senior Principal Researcher, Microsoft Research Amit Sharma, Principal Researcher, Microsoft Research India