RAG & Data Pipelines · 90 minutes
Explain retrieval vs. generation
Explain how documents become evidence for a generated answer, and why an answer can be wrong even when it cites a real document.
1.5 h
Used in interview rounds:
Technical Screen (Easy)Debugging & Evaluation (Easy)AI System Design (Easy)1
Step 1: The question
Explain the ingestion and query paths for a policy assistant. Using S1 and S2, explain why an answer can be wrong even when it cites a real document.
Worked policy example: two excerpts
The following excerpts are fictional.
S1: Returns policy, revision 3, section 1
Unused standard products may be returned within 30 days of delivery.
S2: Returns policy, revision 3, section 2
Custom-printed products are excluded from the standard return window. Report manufacturing defects within 7 days of delivery for review.
2
Step 2: Hints
Optional. Each hint gives a little more away.
3
Step 3: Your answer
Kept in this browser. Saving your score below keeps a copy with it.
0 / 5000
4
Step 4: Reference answer
5
Step 5: Score yourself
Score each dimension 0, 1, or 2, then save the score to your history. Readiness thresholds are editorial estimates.
Grades your written answer against this rubric with your own AI provider key from Settings. It is a second opinion: the score you save is still yours.
0 of 10 · Scored 0 of 5 dimensions
Ready at 8 of 10
Kept in this browser until you sign up, then it moves to your account.
Your saved scores
Practice saves and mock interview answers on this question, newest first.
No saved scores yet. Score every dimension, then save.
6
Step 6: Follow-up questions
An interviewer may ask these next.
How does RAG differ from fine-tuning?
Why does chunking matter?
Does a citation guarantee accuracy?
Why might an uploaded file be missing?
What should happen when evidence is insufficient?
7