Validating expert systems is critical. Without appropriate validation, the system may make costly errors. There are a number of methods of validating expert systems. They can be validated by analyzing and testing the knowledge base and inference engine individually. However, any analysis of the system components is limited to looking at pieces of the system and not at how they work together. The system as a whole can be analyzed by viewing it as a black box and determining the quality of its decisions or by opening up the black box and determining why it made particular decisions.