Clariant is a speciality chemicals company that founded Navigance GmbH in order to venture into their first digital product, a solution that optimizes the productivity of the chemical process. Soon the product team learned that they were facing tough challenges regarding human-machine interaction: For security reasons, the optimization can’t be fully automated. The staff must stay in the loop and take the responsibility of changes in system. But process engineers did not want to have another crowded monitor with cryptic alerts, interfering with their already demanding work routine. They did not trust the recommendations from the black box model. Also, they felt left behind as experts. We will show you how we developed purpose-built data visualizations that explain the machine learning black box. We will talk about how we designed a user interface that puts the users in control and caters to their workflow, ensuring user acceptance.