1. Model Selection intermediate

    A recommendation service's model server is down at peak. Should the application fall back to an older model, precomputed candidates, popularity baselines or cached per-user results — and how is the fallback tested?

    2 min answer fallbackdegradationrecommendationsresilience
  2. Model Selection intermediate

    Your music recommender uses collaborative filtering. Newly released tracks are never recommended. Why, and what do you do?

    2 min answer spotifyrecommendationscold-startensemble
  3. Prompt & Version Management intermediate

    A platform's prompts are embedded in application code and changed frequently. What problems arise, and how should prompts be managed?

    2 min answer prompt-managementversioningevaluationreproducibility
  4. Prompt & Version Management intermediate

    An engineer wants to change the system prompt of a live customer-facing assistant at 16:00 on a Friday. Tell me what has to already be true for that to be a routine change and what you would ask before approving it.

    3 min answer prompt-managementrelease-engineeringrollbackevaluation
  5. Prompt & Version Management intermediate

    Answer quality degraded overnight. No code was deployed. What are the candidate causes?

    2 min answer llmchange-managementobservability
  6. RAG Architecture intermediate

    A business unit wants an assistant answering questions from 200,000 internal documents. They ask whether to fine-tune a model or use retrieval. How do you decide?

    2 min answer airagfine-tuningarchitecture
  7. Reranking intermediate

    A retrieval system's first-stage results are mediocre. Is reranking the right investment, and what does it cost?

    2 min answer rerankingretrievallatencycost
  8. Reranking intermediate

    Retrieval returns 100 candidates and a cross-encoder reranks all of them. The service must hold 300 queries per second at a 400 ms p95 budget for the whole retrieval stage. Roughly what does that rerank cost in hardware and time and does it change the design?

    3 min answer rerankingcross-encodercapacity-planninggpu
  9. Tool Calling intermediate

    An agent resolves support tickets in an average of 8 tool calls. A downstream inventory tool that used to answer in 80 ms starts taking 6 s but still returns correct results. Nothing errors and no circuit breaker trips. What happens, second by second?

    3 min answer tool-callingagentstimeoutsbackpressure
  10. Vector Databases intermediate

    A team needs vector search. When is a dedicated vector database justified over adding vector search to an existing store?

    2 min answer replicatevector-searchdatastoresoperations
  11. Vector Databases intermediate

    A team wants a dedicated vector database for a RAG system over 200,000 documents. Is it necessary?

    2 min answer ragtechnology-selectionpragmatism