In this paper, an artificial intelligent system depending on Case-Based Reasoning (CBR) methodology is about to be used to predict asphalt pavement performance through developing a knowledge-base containing a large number of cases. Each case represents a section of the proposed pavement and contains the main characteristics of the section as well as the performance factors. The predicted performance is used in the evaluation process of pavements and aids maintenance managers in defining maintenance strategies and budget allocation for the whole network. It also aids them to take the suitable actions at the correct times and to set the suitable priorities. Artificial intelligent systems are useful when there are huge numbers of cases or data resulting from yearly counts of field observations on road networks. When the knowledge base increases tremendously, the traditional systems such as expert systems or mathematical models will be not efficient due to time consuming and the difficulties accompanied with dealing with such huge data bases. Pavement performance factors include pavement condition, roughness, deflection, and stiffness. By entering the inputs of a test case that includes the pavement condition index (PCI), roughness (IRI), and maximum deflection (Dmax) into the CBR system, the system will retrieve the most similar case(s) stored in the knowledge base in a very small time. The retrieved case contains the predicted pavement performance of the pavement section. Many trials were being done to define the important features of the case. The retrieved performance is considered the solution of the problem. Many experiments were being done to train and test both the covering of the knowledge base and the retrieval process of the suggested system. It was found that the artificial intelligent system were be successfully used in the prediction of the asphalt pavement performance with acceptable confidence levels.