In recent years, the integration of Artificial Intelligence (AI) into the engineering workflow has emerged as a primary area of interest for simulation professionals. Of particular note is the rise of Geometric Deep Learning (GDL), an approach that can be used to develop fast-running data-driven models that consider the shape and structure of a component. This article represents the experience of a "reasonably" capable simulation veteran, one with a couple of decades of experience in the world of using physics-based solvers, attempting to navigate this new breed of tool for the first time without breaking anything.