The information overflow problem is not simply one of information retrieval and information filtering: the user (reader) might also require aid in summarizing the retrieved information and judging its accuracy and quality. This shows that there is a clear role for the information broker, the human expert that gathers, structures, and evaluates information. Typically information-brokering services of today utilize a predefined classification schema for information. Readers can individualize the service by selecting from the predefined categories. This approach has many disadvantages. First, the individual readers must select between classes of information that may be orthogonal to their real interests. Second, they are forced to use the broker's classification not only for retrieval, but also for structuring the retrieved information. Third, it becomes impossible for readers to indicate that they are looking for types of information that are not covered by the service. Finally, as the information changes over time, the classification schema may have to change. In the EdInfo project [1] we have chosen a different approach. Editors, information brokers, readers, and information services may all use different classification schemas, and change them over time. Techniques from collaborative and intelligent filtering as well as information retrieval are used to create tools that allow services, brokers, and readers to communicate and synchronize their classification schemas.