I have to second the idea, having hacked together something similar myself, to help me complete a literature review——a literature review that I wasn’t planning to publish. Simply generating summaries or pulling key quotes, paper by paper, wasn’t sufficient to be able to understand the topic in the way I wanted to for writing the literature review. In the end, the system would process a collection of hundreds of PDFs that might be related, generate summaries of what they mentioned about the topic in question, and, importantly, was also prompted to note anything about how the insights built upon or were related to insights from previous research, and the motivations behind developing that insight / the challenge it was attempting to solve and whether it was successful. This worked well enough to reduce what might have been weeks worth of work to just a few hours. Genuinely, I believe that research in the near future could look a lot different from what it looks like today.