RAG Engineer

Your dense retriever performs poorly on terse user queries against prose heavy docs. How does HyDE (Hypothetical Document Embeddings) help, and via what mechanism?

Your RAG system's faithfulness metric just dropped from 0.91 to 0.74 while context recall stayed flat at 0.85. What's the most likely pipeline layer to investigate first?

Complete the claim: the two-axis decomposition of RAG eval that diagnoses which layer failed.

Order the layers you'd investigate when debugging a RAG faithfulness regression that just shipped to production, from most likely to least likely cause.

Why do cross-encoder rerankers outperform dual-encoder retrievers at picking the most relevant chunks, given both models can be trained on the same data?

Flashcard: is a 0.85 cosine similarity score from your retriever 'high confidence'?

Which of the following are augmentation sub-decisions in a production RAG pipeline? Select all that apply.

Flashcard: name the three augmentation sub-decisions in a production RAG pipeline.

How do URI templates work in MCP Resources, and how do subscriptions differ from a one-shot read?

What is the key difference between `resources/read` and `resources/subscribe` in MCP?

Explain how MCP differs from RAG and when to choose each approach

How does MCP differ from RAG, and when would you choose one over the other?

Which statements correctly describe the four RAGAS metrics?

Match each RAGAS metric to the specific RAG quality problem it detects

What four metrics does the RAGAS paper propose and what does each measure?

Explain faithfulness vs answer relevance in RAG evaluation with concrete examples

Define faithfulness in RAG evaluation and distinguish it from answer relevance

Explain context recall in RAG evaluation and why it is more expensive than context precision

What does context recall measure in RAG eval and what ground truth does it require?

What does context precision measure in RAG evaluation and what does low context precision indicate?

Predict what slice-level eval reveals about an 85% faithful RAG system suspected to fail on multi-hop queries

Describe two automated hallucination detection techniques and their tradeoffs

What is the main limitation of self-check consistency as a hallucination detection technique?

Clarify the relationship between unfaithfulness and hallucination in RAG systems

Is 'unfaithful' the same as 'hallucinated'? What is the relationship between these concepts?