While most of recent machine translation work has focus on the gisting application (i.e., translating web pages), another important application is to aid human translators. To build better computer aided translation tools, we first need to understand how human translators work. We discuss how human translators work and what tools they typically use. We also build a novel tool that offers post-editing, interactive sentence completion, and display of translation options (online at www.caitra.org). We collected timing logs on interactions with the tool, which allows detailed analysis of translator behavior.