The objective of this work was to use the decision tree technique to define a model capable of predicting water potability. To evaluate the performance of the decision tree classification, a dataset extracted from Kaggle was used, which has 3276 water samples divided by the potability variable. Applying the Pandas and Scikit Learn libraries, a model based on a decision tree evaluated with the metrics of precision, accuracy, completeness, and F1 score was defined, achieving 0.77, 0.80, 0.85, and 0.81, respectively.