An AI prototype that lets you "zoom in and out" of a book

Have had this idea to use LLMs to allow you to “zoom in and out” of a book conceptually, the same way you can zoom in and out on something like Google maps, and go between high-level, and detailed views of the same information. Built out a really rough prototype of some of the backend which uses LLMs to do progressive summarization (making summaries, and then summaries of summaries, etc.) and wanted to show it off here. If folks are interested, or have thoughts, let me know. I am considering building out a nice UI and making this idea into a nice little web app.