A knowledge-based system is an advanced computer program that can solve problems requiring the use of expertise and experience. This feature makes it very suitable for use in dairy farm management. A knowledge-based system contains a knowledge base, an inference engine, and a user interface. In second generation knowledge-based systems, the knowledge base is based upon a model in which declarative knowledge is stored. One of the possibilities for a model is a causal model. Causal models and other knowledge representation schemes can be used in an integrated knowledge-based system for management support on dairy farms. Such a knowledge-based system can contain three modules: 1) a health module, which must, for example, be able to detect and diagnose on-line (subclinical) diseases, such as mastitis, in an early stage; 2) a production module, which must help to reduce and prevent losses from diseases and managerial deficiencies; and 3) a financial module, which must be able to detect suboptimal finanacial results and search for the reasons causing those results. Tools and methods that can be used to build such a large integral knowledge-based system are discussed.