A knowledge base and an inference engine built on top of the hypertext database can add "intelligence" to nodes and links. An interactive filter can be built which will consult with the user and call up the appropriate node. Since hypertext and AI have some common features (semantic dependencies between two pieces of information), research is required to merge the two in order to augment the intelligence of the user [Carlson, 1989]. Halasz reported that "Computation built into the hypermedia system is likely to be more efficient, especially when that computation involves extensive access to information in the network." [Halasz, 1988].