RAG Interview Questions, issue 7, Jul 11, 2026
The Prestige Trap
Senior AI Engineer interview at Google, and the interviewer asks:
“Your RAG system pulls from a SQL database, a private company corpus, and web search. The answers now contradict each other. How do you fix source selection?”
Don’t say: “I’d rank all the chunks by relevance and take the top-k.”
Why PageRank-style routing actively destroys time-sensitive RAG queries, and how to stop treating legacy link topology as an oracle for fresh data.
The full answer, with the mechanism and the arithmetic, is for paid subscribers on Substack.