<p>Historical plant breeding, which optimizes phenotypes through selective crossing guided by phenotypic evaluation and molecular markers, is limited by evolutionary constraints that hinder rapid crop improvement. A new paradigm, precision breeding, circumvents these limitations by targeting genetic variants through functional molecular knowledge. To generate this knowledge at scale, sequence-based deep learning leverages high-quality genome sequence data to predict variant effects at base-pair resolution. When linked to agronomically important traits, these predictions enable breeders to prioritize variants for precision selection or editing. Although it is still in the early stages of development, we foresee three key applications for this approach: introgressing genes from distant breeding pools, purging deleterious mutations and designing new plant ideotypes. Looking ahead, refined computational models will facilitate targeted editing and the systematic redesign of complex physiological processes to address emerging breeding goals under shifting environmental conditions.</p>