I would hope that you're running this on a replica so that the massive table scan doesn't choke writes to the main db. Even then it's possible to bring the replica down and depending on the technology still create a problem (WAL backup for instance)

Another way to bring prod down even with read is depending on your atomicity settings, try starting a transaction and don’t commit or abort it, just leave it dangling. That’s a cute one

How do you validate that the reports are correct? What if an executive makes a wrong business decision because the LLM wrote a wrong SQL query?

> What if an executive makes a wrong business decision

I jokingly tell students, "We all know executives are gonna make bad decisions no matter what the data says. Might as well give them the random numbers more quickly."

The same way we've always done it - glance at it and see if the numbers look like they're within an order of magnitude of what looks reasonable.

so what if there were some numbers in the report which are in actuality, an order of magnitude or two outside of what you think is reasonable, because something was wrong, but the AI agent reports something that looks normal?

So as long as the LLM only makes errors in the single-digit percentage range, everything is peachy. Make number go up, but not by too much.

If you already know the report's numbers, why are you asking an LLM to generate it?

How do you prevent your customer data being used for training?

The same way everyone does, by not using free LLMs, but instead paying OpenAI/Microsoft/Anthropic for an enterprise subscription?

I thought the way is not feeding customer data to the LLM.