Multi-party Conversational Systems are systems with natural language interactionbetween one or more people or systems. From the moment that an utterance is sent toa group, to the moment that it is replied in the group by a member, several activitiesmust be done by the system: utterance understanding, information search, reasoning,among others. In this paper we present the challenges of designing and building multi-party conversational systems, the state of the art, our proposed hybrid architectureusing both norms and machine learning and some insights after implementing andevaluating one on the finance domain.