Honestly, that's the more interesting and more difficult part. Anyone with basic training can be coerced to slice and dice schemas and configs until pretty graphs are produced. LLMs might not even be the best for that.
But knowing _what_ to look for in the data given a problem statement - that's valuable, and hard to teach. LLMs have such a broad base of "knowledge", they can be reasonably good at this in just about any domain.
I would agree -- that's why (to me at least) the recent wave of LLMs is such a big deal. They make semantic contexts accessible for interaction with code logic.
Keen to see more research into this part specially making the questions more specific to the dataset in question and overlaying real-world situations.