Product design based on mechanical performance requirements and with given boundary conditions is a frequent and demanding engineering problem. In most cases, effectiveness of the design is limited to expertise of the respective designer, which also results in inefficient and incomplete exploration of the product's design space. With a large amount of data available and recent advancements in hardware technology, data-driven methods have become an increasingly common strategy for problems that are difficult to formulate or expensive to solve by creating a physical model, but such methods often lack the application perspective; they are not yet widely applied especially in engineering product development. Generative design (here, more precisely generative engineering) is one such technique which has recently gained importance. Although many preliminary studies demonstrate plausible results from data-driven generative design approaches, a closeloop-3D-generative-design-pipeline that achieves full automation and optimization of the design with respect to the product's functional requirements is still in its nascent stage. This paper proposes a generalized hybrid framework comprised of both data-based and physics-based methods to achieve this objective, as represented by the teaser figure 1. An overview of various possibilities for individual modules of the framework is also discussed.