Dipartimento di Ingegneria informatica, automatica e gestionale

AI-augmented Business Process Management Systems (ABPMSs) are an emerging class of process-aware information systems empowered by AI technology for autonomously unfolding and adapting the execution flow of business processes (BPs). A central characteristic of an ABPMS is the ability to be conversationally actionable, i.e., to proactively interact with human users about BP-related actions, goals, and intentions. While today's trend is to support BP automation using reactive conversational agents, an ABPMS is required to create dynamic conversations that not only respond to user queries but even initiate conversations with users to inform them of the BP progression and make recommendations to improve BP performance. In this paper, we explore the extent to which state-of-the-art conversational systems (CSs) can be used to develop such proactive conversation features, and we discuss the research challenges and opportunities within this area.