The growing concern about environmental pollution, notably water pollution, has driven the development of more efficient and sustainable wastewater treatment technologies. Among them, adsorption stands out for its effectiveness, low cost, and the possibility of regenerating adsorbent materials. However, optimizing this process using traditional methods demands time, cost, and a high number of experiments. In this context, artificial intelligence (AI) emerges as a promising alternative for modeling and predicting the behavior of adsorptive systems with high precision. This chapter presents the main AI models applied to adsorption, including artificial neural networks, support vector machines, and models based on decision trees, discussing their advantages, such as greater efficiency, resource savings, and the ability to identify relevant variables, compared to conventional experimental methods. The limitations of using AI are also addressed, such as the need for robust databases and the risk of overfitting. Computational tools, such as Python, R, and MATLAB, are discussed as means of practical implementation. Finally, examples of AI applications in adsorption processes are presented, highlighting its potential in predicting adsorptive capacity and optimizing operating conditions.