This is kind of dumb because with agentic tooling, the input to the model is whatever it looks at. Sure, I'll send you the prompt along with a design document and the entire transcript of a meeting. That'll be useful.
It would be useful! People send me design documents and meeting transcripts all the time. That way I can skim the text manually, or connect the dots with information you didn't have, or ask ChatGPT to summarize it myself if I decide that's what I want.