adapt.citrination is a cloud-based data informatics platform specific to additive manufacturing data that has been collaboratively developed by Citrine Informatics and Colorado School of Mines, and is populated with data from ADAPT R&D programs and industry partners. Its machine learning Design of Experiments (DOX) tool provides statistical reports and models, data visualization tools (including dimensionality reduction), uncertainty quantification, and error metrics for the models. It uses a combined outlier and uncertainty metric to inform the user of the most important experiments to perform next to gain the biggest statistical improvements within a given data space; that is, it simultaneously considers accuracy, precision, bias, and variance of the data model in prioritizing the next experiments to perform. A multivariable constrained optimization tool guides the recommendations, allowing users to prioritize coupled figures of merit within the design space, such as minimizing porosity while maximizing strength and stiffness.Collectively, this platform greatly reduces time and cost by reducing the number of experiments needed to reach statistical certainty in a data model of a given design space. Simulations, such as crystal plasticity models of the development of thermal stresses, can be used as inputs for the knowledge base equally as well as experimental measurements.