The biggest realisation for me while making ChatBotKit has been that UX > Model alone. For me, the current state of AI is not about questions and answers. This is dumb. The presentation matters. This is why we are now investing in generative UI.
Google Gemini were showing something that I'd call 'adapted output UI' in their launch presentation. Is that close to what you're doing in any way?
You can find some open-source examples here https://github.com/chatbotkit. More coming next week.