My prompt-injection fix caught 0 of 20 attacks. The part I almost didn't build caught all of them.
I built a checker for AI-drafted answers to retirement questions ( retirement-answer-check ). Before a customer sees a draft, it decides SEND or REVIEW. Plain code checks every number against an IRS-sourced facts table. Two model "judges" handle what code can't read: non-numeric wrong facts ("yes, that exception covers
