The processing of incoming sensory information relies on interacting mechanisms of sustained attention (the ability to focus attention and ignore irrelevant stimuli) and attentional capture (the ability of certain stimuli to reflexively attract one’s attention). Being able to precisely predict what can capture attention when it is engaged in a demanding task is important both for understanding the nature of attention as a cognitive system and also for practical applications. While evidence indicates that exogenous capture, a mechanism previously understood to be automatic, can be eliminated while concurrently performing a demanding task, we reframe this phenomena within the theoretical framework of the ‘attention set’ (Most et al., 2005). Consequently, the specific prediction that cuing effects should reappear when dimensions of the cue overlap with those in the attention set (i.e., elements of the demanding task) was empirically tested and confirmed. Suggestions for further theoretical refinement and empirical testing are discussed.