We design applications that use AI models, more specifically, Deep Learning models, in order to both locate and identify entities and objects in images (2D and 3D) and videos. Some of the models we use are advanced varieties of the Convolutional Neural Networks, which will normally bear other structures enclosed (specific models of Recurrent Neural Networks or of Generative Adversarial Networks) in order to achieve the necessary specificity required by the customer in a particular case scenario. Should this process be very extensive, it may require the rental or purchase of new high-performance hardware.