Food security is threatened by climate change, with heat and drought being the main stresses affecting crop physiology and ecosystem services, such as plant-pollinator interactions. Despite the increasing relevance of flowers in sensing the stress, phenotyping platforms aim at identifying genetic traits of resilience by assessing the physiological status of the plants, usually through remote sensing-assisted vegetative indexes, but find strong bottlenecks in quantifying flower traits and in accurate genotype-to-phenotype prediction. However, as the transport of photoassimilates from leaves (sources) to flowers (sinks) is reduced in low-resilient plants, flowers are better indicators than leaves of plant well-being. Indeed, the chemical composition of flowers changes in response to heat and drought, as it does the amount of pollen and nectar that flowers produce, which ultimately serve as food recourses for the pollinators. DARkWIN proposes to track and rank pollinators’ preferences for flowers of a tomato mapping population exposed to heat and drought as a measure of functional source-to-sink relationships. To achieve this goal, DARkWIN will develop a pollinator-assisted selection and phenotyping platform for automated quantification of Genotype x Pollinator x Environment interactions through a bumblebee geo-positioning system. Pollinator-assisted selection for agriculture will be validated by a multi-omics dataset of unprecedented dimensions in a mapping population of tomato, including floral metabolic, transcriptomic, and ionomic traits, as well as mapping candidate genes, linking floral traits, pollinator preferences, and plant resilience. Moreover, DARkWIN will deliver tomato F1 pre-commercial varieties based on the natural biological process of pollinatordriven selection under climate change conditions. This radical new approach can change the current paradigm of plant phenotyping and find new paths for crop breeding assisted by ecological decisions.