Task preparation has traditionally been thought to rely upon persistent representations of instructions that permit their execution after delays. Accumulating evidence suggests, however, that accurate retention of task knowledge can be insufficient for successful performance. Here, we hypothesized that instructed facts would be organized into a task set; a temporary coding scheme that proactively tunes sensorimotor pathways according to instructions to enable highly efficient“reflex-like”performance. We devised a paradigm requiring either implementation or memorization of novel stimulus–response mapping instructions, and used multivoxel pattern analysis of neuroimaging data to compare neural coding of instructions during the pretarget phase. Although participants could retain instructions under both demands, we observed striking differences in their representation. To-be-memorized instructions could only be decoded from mid-occipital and posterior parietal cortices,consistent with previous work on visual short-term memory storage. In contrast, to-be-implemented instructions could also be decoded from frontoparietal“multiple-demand”regions, and dedicated visual areas, implicated in processing instructed stimuli. Neural specificity in the latter moreover correlated with performance speed only when instructions were prepared,likely reflecting the preconfiguration of instructed decision circuits. Together, these data illuminate how the brain proactively optimizes performance, and help dissociate neural mechanisms supporting task control and short-term memory storage.