This article presents the Cogni-CISMeF project, which aims at improving the health information search engine CISMeF, by including a conversational agent that interacts with the user in natural language. To study the cognitive processes involved during information search, a bottom-up methodology was adopted. An experiment has been set up to obtain human dialogs related to such searches. The analysis of these dialogs underlines the establishment of a common ground and accommodation effects to the user. A model of artificial agent is proposed, that guides the user by proposing examples, assistance and choices.