Preventive quality management (PQM) is a very information-intensive task. Information as diverse as customer requirements, material specifications, and production line characteristics of a product as well as complaints related to similar products have to be taken into consideration when, e.g., predicting and evaluating possible failure modes of a product. However, only a subset of this information is actually relevant in a given stage of the PQM process and for a given person. In this paper, we exploit the notion of context to restrict the number of information sources accessed, make information selection more goal-directed, and finally, to customize system-user interaction.