Integration of new utterances into context is a central task in any model for rational (human-machine) dialogues in natural language. In this paper, a pragmatics-first approach to specifying the meaning of utterances in terms of plans is presented. These plans are computed during a dialogue on the basis of information about the current situation that is updated continually. New contributions are integrated into a dialogue if they help in establishing a new plan, or if they deliver important information for executing an already established plan.