Many intelligent agents need knowledge and information to support their reasoning and problem solving. The World Wide Web is a vast, open, accessible and free source of knowledge, but virtually all of it is encoded as natural language text — a form difficult for most agents to directly understand. We describe initial work on adapting a mature language understanding agent to process Web text and publish its output in the SemanticWeb language OWL. This approach adds knowledge on the Web in a form designed for agents to use. Moreover, language understanding agents can use the growing knowledge on the Semantic Web in their own language understanding tasks. Importing and exporting knowledge in the different knowledge representation formalisms used by these agents poses significant challenges. In particular we need to bridge the gap between the representation features of traditional non web-based representations and newer web-based formalisms such as OWL.