AI methods, especially deep networks, have strong predictive skills for Earth System variables yet are limited in interpretability and cannot alone answer specific scientific questions. Here we argue that the genes of AI, meaning its most transformative core ideas bringing forth favorable traits, can be absorbed into traditional modeling domains to give us new ways of making inquiries. For example, a genre of physics-informed machine learning, called “differentiable” modeling (DM, https://t.co/qyuAzYPA6Y), trains neural networks (NNs) with process-based equations (priors) together in one stage (called “end-to-end”) to benefit from the best aspects of both paradigms. DM inherently enables physical interpretation, extrapolates well in space and time, and leverages efficient AI computing infrastructure. We demonstrate the progress of evolving process-based model structures and parameterization to produce state-of-the-art hydrologic or ecosystem predictions that rival purely data-driven machine learning, or to correct climate forcings using hydrologic data, all using the DM methodology. We provide novel and large-scale modeling capabilities in river flow & transport, ecosystem, and water quality. We further demonstrate how to learn previously poorly-understood relationships such as runoff spatial scaling, i.e., how runoff per catchment area and climate sensitivities vary as a function of catchment scale, or vegetation acclimation functions, i.e., how vegetation parameters vary as a function of environmental variables. As another example of AI “genes”, generative AI can capture the conditional joint distribution of multiple variables, accumulating knowledge from all forms of observations and informing on scarcely observed processes - thus it can be leveraged to capture the coevolution of environmental variables. Tools with AI genes can serve as the basic infrastructure that democratizes access to reliable predictions and gives wings to solutions for some of the most elusive and important environmental modeling problems.