“There doesn't seem to be a very good accountability mechanism here,” said Victoria resident and frequent police critic Stephen Harrison, who obtained the documents. “Literally nobody other than the individual officer has access — you wouldn't even know that they're using it.”
You’re wrong on the first count primarily because you presume RAG retrieval isn’t deterministic. Which it is, even if you format the question differently - as long as the request is coherent and covers the same topic, RAG lookup should be roughly the same, and that should result in the same RAG entries surfaced.
At which point it’s the prompt (the hidden/system prompt, not the end user’s basic question) that determines just how well that RAG data gets displayed and potentially reworded. But as long as it’s essentially used as a human language lookup system + summarisation, its reliability should be generally pretty good, on par with having an on-site paralegal.
If the output is different every time, even subtly, then the overarching system is non-deterministic. If you need to rely on the output to be accurate either for safety, reliability, liability or any combination of the three then it must be verified by every time and your benefit in not using the human that can actually be held accountable for the output is severely limited.