A multi-session experiment explored the relationship between individual differences and the development of strate-gies in a complex task environment. In the first session, participants completed measures of working memory and adaptivity.Participants then performed 4.5 hours of a multitasking activity that involved prioritizing, selecting, and sorting objects intobins under time pressure. The analyses reported here focus on how participants prioritized objects in a queue of objects andselected objects from that queue for sorting. Priority selection strategies were automatically extracted using machine learningmethods. Differences in strategy use were related to measures of working memory and adaptivity. Strategy use and strategychange mediated the relationship between task performance and individual differences. A hierarchical clustering analysis re-vealed patterns of strategy shifts that distinguished between participants who improved and those who did not. These resultsprovide a basis for examining strategy training geared toward individuals’ cognitive abilities.