Adaptive learning is a method that individualizes teaching-learning strategies according to learners’ needs and preferences. This paper describes the design, implementation, and testing of a web application developed using adaptive learning that aims to improve students’ knowledge acquisition in the subject of Graphic Expression in Engineering. The tool uses a predictive algorithm, is adaptable in a personalized way to the student, and presents content adjusted to their cognitive needs. The application determines the student’s progress within the content of the subject, which is classified by the branches of knowledge. The tool was tested at the Barcelona East School of Engineering (EEBE), Universitat Politècnica de Catalunya (UPC). The system is active when the student performs daily activities corresponding to the content to be reviewed, which varies in complexity in real time depending on the student’s interaction with the system. Once the activity is completed, it is assessed with an algorithm that can use the results of other students to predict the activities they will perform as a result of their work. The results not only improved the grades of the evaluations, but also improved heuristic decision-making on the content to be taught by incorporating them into their assessment processes.