The ability to explain our models’ decisions is recently emerging as a standard requirement for models with a high impact on people’s lives. This necessity may pose several challenges, as most models used in the industry are not inherently explainable. Today, the most popular explainability methods are SHAP and LIME, each having its own disadvantages but offering convenient APIs, backed by solid mathematical foundations. In this talk, I will introduce a relatively new model explanation method – Counterfactual Explanations (CEs). CEs explanations which are based on minimal changes to a model input features, that lead the model to output a different (mostly opposite) predicted class. CEs have been shown to be more intuitive for humans to comprehend and provide actionable feedback to the end user – e.g. what can the user change in order to get a previously declined loan to be approved. I will review the different challenges in this novel field (such as how to ensure that the CE proposes changes which are feasible), provide a birds-eye view of the latest research and give my perspective, based on my research in collaboration with Tel-Aviv University, on the various aspects in which CEs can transform the way we understand our models.