CrackML by @ml.with.umang
Interview questions / GenAI & LLM
GenAI & LLM interview question

Design RAG with strict source control

Design RAG with strict source control.

hardconceptEvidence 31/1002 source reportsAppleScale AI

The 60-second answer

Build RAG as ingestion/chunking, embedding/indexing, retrieval, optional reranking, prompt construction, and generation. Evaluate retrieval recall separately from grounded answer quality.

Build the answer in this order

1
Define the mechanism

Build RAG as ingestion/chunking, embedding/indexing, retrieval, optional reranking, prompt construction, and generation.

2
Explain the architecture

Evaluate retrieval recall separately from grounded answer quality.

3
Compare trade-offs

Preserve citations and metadata so generated claims can be traced to evidence.

4
Close with serving + evaluation

Add abstention/fallback behavior when retrieval confidence or coverage is weak.

A useful interview mental model

This is the shape of a strong answer—not a script to memorize.

01Definition
02Mechanism
03Trade-offs
04Failure modes
05When to use

Senior-level signal

  • Handle ACLs, freshness, deletion, and index versioning as first-class requirements.
  • Diagnose retrieval failure separately from generation failure before tuning the LLM.

What the interviewer is really testing

Understanding beyond prompting: architecture, retrieval, evaluation, inference, safety, latency, cost, and failure recovery.

Likely follow-up questions

What assumption makes this approach work?
When would you choose the strongest alternative instead?
What production or data failure mode changes your answer?

Common weak-answer patterns

  • Reciting a definition without mechanism or assumptions.
  • Claiming one technique is always better without a data regime.
  • Stopping before failure modes, validation, or deployment implications.