In this paper, I present a human-machine, collaborative, 3D modeling system that combines human gestures with generative 3D modeling. The project seeks to explore the unfolding of design ideas while reframing the concept of design workflows, knowledge encapsulation, disembodiment, and representation in 3D CAD processes. Using machine learning and interactive computation, this project links user sketches to generative 3D modeling using a sequence-to-sequence model. By encapsulating expert knowledge related to 3D modeling, this project seeks to eliminate intermediate representations, such as, sections, elevations, and floorplans, in the design process to engender immediate, real-time, 3D model generation from hand sketches (Figure 1). Whereas, most of the projects using generative machine learning to produce 3D models focus on the one-to-one fidelity between sketches and 3D models, this research focuses on the generative power of gesture sequences to generate novel 3D models. This experiment aims to answer, among others, the following questions: Can the use of machine learning reframe the generation of 3D models in a more embodied way? Is it possible to capture design intentions from sketches to generate 3D shapes using machine learning? Can we design and explore ideas inside a computer without representing them, but focusing on the unique sequences that originate novel designs?.