PIES is a knowledge system for interpreting the parametric test data collected at the end of complex semiconductor fabrication processes. The system transforms hundreds of measurements into a concise statement of the overall health of the process, and the nature and probable cause of any anomalies. A key feature of PIES is the structure of the knowledge-base, which reflects the way fabrication engineers reason causally about semiconductor failures. This structure permits fabrication engineers to do their own knowledge engineering, building the knowledge base, and then maintaining it to reflect process modifications and operating experience. The approach appears applicable to other process control and diagnosis tasks.