In this paper, we describe an intelligent agent that delivers learning materials adoptively to different students, factoring in the usage history of the learning materials, the student static background profile, and the student dynamic activity profile. Our assumption is that through the interaction of a student going through a learning material (i.e., a topical tutorial, a set of examples, and a set of problems), an agent will be able to capture and utilize the student's activity as the primer to select the appropriate example or problem to administer to the student. In addition, our agent monitors the usage history of the learning materials and derives empirical observations that improve its performance. We have built an end-to-end infrastructure, with a GUI front-end, an agent powered by case-based reasoning, and a multi-database backend. Preliminary experiments based on a comprehensive simulator show the feasibility, correctness, and learning capability of our methodology and system.