The first 3D Deep Learning Software dedicated to Computer Assisted Engineering and Design. Better design choices, faster R&D cycles, reduced engineering costs. Neural Concept Shape (NCS) is the commercial and industrial implementation of a software package developed at EPFL’s computer vision laboratory over the last 3 years. NCS is the first Deep-Learning software specifically tailored for Computer Assisted Engineering application. Our software allows the engineer to extract maximum value from simulation data, allowing him to explore an infinite number of designs without calling back the expensive simulator and to automatically optimize a shape given a set of performance goals. Our software searches the space of shapes to find this best compromise, while saving the engineer time, energy and economical cost. Neural Concept Shape is a force multiplier that will make it possible to test several orders of magnitude more variations of a given design than is currently possible. This results in far more optimised shapes and potentially, to solutions that a human designer may not have previously considered. One of the main innovation is that Neural Concept Shape is agnostic to the shape parametric representation, as it directly works with the mesh representation of the design. Hence, a single predictor can be trained with a large amount of data, used for various optimisation tasks and becomes more and more powerful over time. The approach can leverage additional historical data from many different sources, without the need of having multiple designs sharing an underlying parametrisation.