I'm currently building a hybrid experience where users can have long conversations for things like conversation practice, while the bot also having the ability to present Anki-style flashcards. I'm also exploring other modalities for "cards" such as questions that would allow the user to respond to the bot's question with a voice message, and having the system analyze the recording for pronunciation/tone issues. Weaving these multiple modalities into a seamless experience is something that I'm still working on.