The goal of this paper is to deal with a problem hardly ever addressed in natural language generation, conceptual input. In order to be able to express something, one needs to have something to express to begin with: ideas, concepts and thoughts. The question is how to access thoughts and build their representation in form of messages. What are the building blocks? How to organize and index them in order to allow for quick and intuitive access later on?It is generally believed that ideas precede expressions. Indeed, meanings, imprecise as they may be, tend to precede their expression in language. Yet, message creation is hardly ever a one-step process. Conceptual inputs are generally abstract and underspecified, which implies that they need to get refined later on, possibly even during the expression phase.In this paper we investigate interactive sentence generation, the focus being on conceptual input, a major component of language generation. Our views will be illustrated via three systems: ILLICO, a system for analyzing/generating sentences and guiding their composition; SPB, a multilingual phrase-book with on the fly generated audio output and Drill Tutor (DT), an exercise generator. While ILLICO is a message-understanding system with a message-completion functionality, SPB and DT are message-specification systems. The user works quite early with fairly complete structures (sentences or patterns), making basically only local changes: replacing words in the case of SPB, and choosing them to instantiate pattern variables in the case of DT.M. Zock ( ) · P. Sabatier · L. Jakubiec