This paper describes a system, Mr.Web, designed to interact with users over email to create and update Web pages. Our goal is that users interact with Mr.Web as if it were a human Webmaster. We collected 325 examples of people writing email requests to a Webmaster, and used this to generate the semantics of Mr.Web's email parser. The results of the survey indicate that the limited context of a Webmaster gives us a reasonable subset of the natural language processing (NLP) problem. This paper explains the system design, user study results, and plans for future work. Keywords Human-Computer Interaction, Natural Language Processing