Improving Web search technology is a hot topic. Typically, a search engine does not need to understand the documents it is accessing. But what if the document collections we want to search are very domain specific or limited in size? Wouldn't it be useful to have a simple a dialogue system that knows what data is available and can help a user during the search process? Furthermore, shouldn't such a system be portable enough to run on a completely different collection without much hassle? The author presents such a search system, which is based on a generic framework that incorporates a simple domain?independent dialogue manager and an automatically created model of the domain.