This chapter explores the potential use of artificial intelligence (AI) in cochlear implant (CI) science, focusing on two distinct applications: postoperative hearing outcome prediction from preoperative data and CI parameter fitting. A comprehensive overview of the current state of the art, recent advancements, and the challenges of adopting AI in these areas is presented. Regarding outcome prediction, various preoperative data features and machine learning (ML) models (e.g., linear models, artificial neural networks, random forest models, gradient boosting models, and support vector machines) are explored in both postlingual and prelingual adults and children. Despite some improvements provided by ML-based models, they are not yet widely used in practical applications due to generalization issues and a lack of data acquisition standardization. Concerning parameter fitting, which is a crucial process in maximizing the individual performance of CI recipients, researchers are looking for AI-based fitting methods to offer faster and potentially more effective solutions than manual fittings. A few AI-based fitting methods, such as genetic algorithms, reinforcement learning, and stochastic approaches like the one used in the fitting to outcome expert (FOX) method, are detailed and linked together as different members of a broader generic family. Despite the promising progress in genetic algorithms and some interest in using FOX in certain clinics, AI has yet to find its solid footing in practical CI fittings.