WebRat is an interactive system for visualising and refining search result sets. Documents matching a query are dynamically clustered on the fly and visualised as a contour map of islands. Thematic clusters are built, analysed, and visualised in real time. Users can interactively explore the visualisation and refine queries by selecting from the keywords and clusters presented to them. WebRat does not rely on precalculated meta data. Instead, necessary information is directly extracted from query result representations provided by search engines, as for example ranked lists of document snippets. The system is language-independent and can easily be adapted to a number of data sources and visualisation modes. WebRat supports agile knowledge retrieval by transforming unstructured information input into a representation enriched with structure and meta information even when environmental conditions and user demands change frequently and rapidly.