Additive manufacturing (AM) is an innovative technology that offers new manufacturing possibilities across various industries. However, its integration into conventional manufacturing systems remains limited due to insufficient quality assurance for the parts produced. Machine learning (ML) has recently gained widespread adoption in numerous fields, offering significant advantages in cost reduction and processing efficiency. By applying ML, manufacturers can predict and ultimately control the mechanical properties of AM-fabricated parts, taking into account variations in printing parameters such as temperature and speed. This study reviews the current technologies employed in 3D metal printing, focusing on optimizing parameters to produce high-quality prototype parts. In the automotive sector, where reducing the number of prototypes is a priority due to high tooling costs, metal 3D printing presents a promising alternative. However, testing and validation protocols for AM parts remain limited. This study provides a critical examination of the subject, with the potential to significantly reduce product development timelines.