One of the critical reasons for failed IS projects is the inability to accurately meet user requirements, resulting from an incomplete or inaccurate collection of requirements during the requirements elicitation (RE) phase. While interviews are the most effective RE technique, they face several challenges that make them a questionable tool for the numerous, heterogeneous, and geographically distributed users of contemporary IS. There is a lack of tool support to conduct interviews with a wide audience. While initial studies show promising results in utilizing text-based conversational agents (chatbots) as interviewer substitutes, we lack design knowledge for designing AI-based chatbots that leverage established interviewing techniques in the context of RE. In this research we focus on designing chatbot-based interviewing in order to collect vast amounts of qualitative data.