Conversational agents are becoming increasingly popular for supporting and facilitating learning. Conventional pedagogical agents are designed to play the role of human teachers by giving instructions to the students. In this paper, we investigate the use of conversational agents to support the 'learning-by-teaching' paradigm where the agent receives instructions from students. In particular, we introduce Curiosity Notebook: an educational application that harvests conversational interventions to facilitate students' learning. Recognizing such interventions can not only help in engaging students within learning interactions, but also provide a deeper insight into the intricacies involved in designing conversational agents for educational purposes.