GO TO A SECTION

↑ ↓ to navigate · Enter to openExplore all sections →
FDEInterviews logo
← RAG & Agent System Design / 38
hardOpenAICohereGlean

RAG accuracy dropped 12 points in production this week and nobody shipped a prompt change. Debug it.

The classic 'it regressed and the prompt is untouched' triage. The answer that scores walks a decisional tree from retrieval to generation and names the silent culprit most candidates miss: the embedding stack changed under you.

Updated Aug 2026 · Grounded in real Forward Deployed Engineer interview loops and written to a senior-engineer editorial bar.

The classic 'it regressed and the prompt is untouched' triage. The answer that scores walks a decisional tree from retrieval to generation and names the silent culprit most candidates miss: the embedding stack changed under you.

20 answers per topic instead of 10, plus saved progress and bookmarks · no cardor unlock all 548 remaining answers · ₹2,000 / $25

Every answer, concept and course, every paper breakdown, all published video lessons, hands-on FDE Lab missions, Premium PDF guides and companion files, the full practice-test bank and work-sample downloads. Referral Premium excludes guide PDFs and their companion files.

6 months · One payment · No auto-renewal

Study alongside free video lessons.

Related course lessons

Keep practising

Learners often go here nextA multi-hop agent feels sluggish at p95. Design its latency budget and cut tail latency without swapping models.PremiumNext in this trackYou have no labels on production traffic. How do you monitor RAG retrieval quality before users complain?PremiumNext in this trackYour agent reads customer emails, queries a private database, and can send messages. Harden it against prompt injection.Premium
DISCUSSION · 0

No comments yet — be the first to share your approach.