Distributed problem solving on the web is becoming more and more important. Client server architectures are often confronted with server overload. The process of browsing a large number of alternative solutions is particularly tedious. In this paper, we present s methodology for distributing the computation between server and client. The ides is to formalise the problem as s constraint satisfaction problem (CSP). This formalisation supports a natural decomposition of the task into two subtasks: generation of the CSP by the server from its database, and generating and browsing the solutions on the client. In this way, the browsing process runs locally and can be very fast, while the server is only accessed once during the pro. ceas. We provide the :lava Constraint library (JCL) for implementing the agent that solves the CSP on the client. We illustrate the concept on the example of planning air travel.