GO TO A SECTION

↑ ↓ to navigate · Enter to openExplore all sections →
FDEInterviews logo
← RAG & Agent System Design / 64
hardSierraDecagon

Your support agent resolved 69% of conversations last month and 60% this week. Nobody deployed anything. What do you check first?

Nobody deployed anything is true of your repository and false of the system. The model provider, a tool behind an API, the knowledge base and the traffic mix all change without a commit. Segmentation comes before theory: a broken intent and a mix shift produce the same headline and need different fixes.

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

Nobody deployed anything is true of your repository and false of the system. The model provider, a tool behind an API, the knowledge base and the traffic mix all change without a commit. Segmentation comes before theory: a broken intent and a mix shift produce the same headline and need different fixes.

20 answers per topic instead of 10, plus saved progress and bookmarks · no cardor unlock all 545 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.

Keep practising

Next in this trackDesign a simulated-customer regression suite for a support agent in production. What does it catch, what does it miss, how big must it be?PremiumNext in this trackBuild the eval for a text-to-SQL feature over a customer's warehouse: what is in the golden set, what is the metric, how many cases?PremiumNext in this trackA chunking change shipped last week. Aggregate recall barely moved, and support says answers got worse. Find the regression.Premium
FEDITOR'S NOTE

This is a final-round prompt at the agent companies, and it is scored on order of operations. The strong candidate decomposes the metric before naming a cause, distinguishes a broken intent from a changed mix in the first table they draw, and ends with the regression suite that would have caught it before customers did. The weak candidate says 'the model probably drifted' and starts reading transcripts at random.

DISCUSSION · 0

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