There is some nuance here when talking about grid search and CV. When you ask DataRobot to perform a grid search, it will of course try to determine which hyperparameter value(s) "won" by computing scores for tuned models within the defined grid. To do this DataRobot will automatically generate an internal "grid search" partition inside of the training dataset. Typically the partition is a 80/20 training/validation split, although in some cases DataRobot applies five-fold cross-validation. This means that DataRobot will automatically decide how to partition based on both partition settings input by the user during initial project creation, AND internal partition criteria that DataRobot engineers and data scientists have found to be optimal for doing a grid search with the chosen hyperparameter(s). Therefore, once a project is setup and initial models are generated, the user relies on DataRobot automation to choose partitioning as CV or otherwise.