RAG Interview Questions, issue 13, Jul 17, 2026
The Flat Index Trap
Senior AI Engineer interview at Google, and the interviewer asks:
“Your RAG pipeline scores 90% on factual lookups but collapses on ‘summarize this 300-page report.’ Why, and don’t tell me it’s chunk size?”
Don’t say: “I’d increase the chunk size”
Why relying on contiguous chunks makes your RAG pipeline silently collapse on global themes, and how treating abstraction as a retrievable object lets your queries pick their own altitude.
The full answer, with the mechanism and the arithmetic, is for paid subscribers on Substack.