In the oil and gas industry, the implementation of an artificial lift system is utilized to enhance the extraction of hydrocarbons from a reservoir that has depleted its natural energy. This can be achieved by employing pumps such as positive-displacement or centrifugal downhole pumps, or by injecting gas into the well tubing to reduce liquid hydrostatic pressure and improve fluid flow towards the surface. Recently, artificial intelligence-based algorithms have emerged as the leading approach for modelling various artificial lift parameters and problems. Consequently, there has been a renewed interest in understanding the role and effectiveness of different computational algorithms used in the artificial lift system domain. While there is an extensive body of literature on this subject, no prior research has effectively consolidated the findings from various artificial lift system domains, underscoring the need for an all-encompassing review. The purpose of this review is to create a guide that serves as a framework that helps scholars identify knowledge gaps and suggest novel ideas that would enhance the workings of artificial lift systems in the oil and gas industry. This article presents the first comprehensive analysis of artificial intelligence applications in five key areas of artificial lift systems in the oil and gas industry namely: prediction of oil and gas flow rates in artificial lift wells, prediction of artificial lift system failures, selection of artificial lift systems, parameter optimization, and the application of soft sensing technologies in artificial lift systems. The research studies pertaining to each of these areas were systematically identified from the existing literature, and their main features were highlighted. To ensure the uniqueness and novelty of this work, a critical evaluation of the artificial lift articles in each broad area was conducted. The review outcomes were then presented in clear tables that highlighted the main features of each study. Findings from the study indicate that artificial intelligence models are prevalent in almost every aspect of artificial lift systems, and the number of articles on this topic continues to grow. Some of these models have even been field tested and proven effective in improving artificial lift system operations and reducing costs. However, there is need to enhance the explicitness and interpretability of some of the predictive models by including vital details, to enhance seamless implementation and easy deployment in the field. This work will be valuable for industry operators, researchers, and students who seek a guide or reference material on artificial intelligence-based models for artificial lift systems. © 2024 Elsevier Ltd