The dental example is a good illustration of why "sounds grounded" and "is grounded" need separate tests. One small addition that's cheap to run alongside your Monday audit: a regression set built from your own policy exceptions.

1. Pull the 15–20 policy rules that have a catch (new patients only, within 60 days, excludes sale items, and so on).
2. For each, write a question from the customer the rule excludes, not the one it covers.
3. Run them weekly and have a reviewer check three things: does the answer match the exception, does it name a source, and does that source exist on your allowlist?

A reviewer prompt that works well: "Here is the policy text and the agent's answer. Quote the exact sentence from the policy that supports each claim. If you can't quote one, mark the claim UNSUPPORTED."

Exclusion questions are where inverted answers hide, since happy-path spot checks never touch them. Thanks for the checklist.