The use of Artificial Intelligence approaches like Machine Learning (ML) for process optimization promises significant benefits in modern production. One of the most important tasks while using ML methods is feature engineering. The common feature engineering methods are either very time-consuming or require a deep understanding of the process data, that is, knowledge of the basic causality relations in the process. Therefore, due to the increasing complexity of equipment and processes, as well as the necessity to reduce the time to market for new solutions, feature engineering is becoming a challenge to the successful application of ML. This article presents a holistic feature engineering approach showing how the use of integrated software for experimental process analysis can significantly reduce the time spent on feature engineering while improving its quality. The considered target application is the tool wear monitoring on an example of a drilling process based on minimal available measurements.