This work proposes the definition of an Adaptive Conversation-based Learning System (ACLS) able to foster computer-mediated tutorial dialogues at the workplace in order to increase the probability to generate meaningful learning during conversations. ACLS provides a virtual assistant selecting the best partner to involve in the conversation and generating adaptive feedbacks for the dialog. Adaptive feedbacks are triggered by the concepts automatically extracted from the conversation texts, while their content is generated by querying the organizational knowledge represented by means of Semantic Web technologies. Lastly, Fuzzy Formal Concept Analysis is exploited to conceptualize domain knowledge. [For the full proceedings see ED562127.]