For millennia, natural and artificial selection has combined favourable alleles for desirable traits in crop species. While modern plant breeding has achieved steady increases in crop yields over the last century, on the current trajectory we will simply not meet demand by 2045. Novel breeding strategies and sources of genetic variation will be required to sustainably fill predicted yield gaps and meet new consumer preferences. Here, we highlight that stepping up to meet this grand challenge will increasingly require thinking beyond the gene. Significant progress has been made in understanding the contributions of both epigenetic variation and cis-regulatory variation to plant traits. This non-genic variation has great potential in future breeding, synthetic biology and biotechnology applications.