INFOrmer is an intelligent filtering system, currently being applied to the management of USENET News articles. An individual may have one or more profiles, each representing a long-term interest of that user. The user prole is then used to measure the relevance of incoming articles and lter out irrelevant documents. A user profile may be modified as a result of relevance feedback, so that it adjusts to users' changing interests. This paper discusses the architecture of INFOrmer and covers the profile/document representation and comparison techniques adopted within the system.