Every learner has a unique learning style and learning requirements. This represents an important concept in adapting e-learning content to meet the specific needs of each and every learner. Due to the rise of technology, personalization refers to all elements of customizing a system’s interactions and information content with its users. The major emphasis of this research is on personalization, which is when a system develops tailor-made services about a person’s objectives, interests, and preferences, tailors’ interaction and material, and provides the most appropriate user experience. Adaptive educational systems can make use of a variety of AI approaches. In this research, a model using AI for personalization of learning content is proposed. This system generates exercises based on their lecture notes and provides their score for each exercise. A pre-trained dataset, SQuAD (Stanford Question Answering Dataset), is used to train the model. T5, an encoder-decoder model that has already been trained on a variety of tasks that are both supervised and unsupervised, and are each translated into a text-to-text format. This was then evaluated using ROUGE Metrics. This research proposes a novel approach that helps the learners consolidate their learning materials through a personalized learning pathway.