Home / GenAI Engineer practice test / Evaluation and Monitoring / Question

Databricks Generative AI Engineer Associate · free practice question

A company employing a Retrieval Augmented Generation (RAG) system is facing unexpectedly high monthly expenditures for its Large Language Model (LLM) API…

Exam-style question on Evaluation and Monitoring from the free GenAI Engineer practice test, with the answer and a full explanation below.

Updated November 11, 2026

Evaluation and Monitoring

A company employing a Retrieval Augmented Generation (RAG) system is facing unexpectedly high monthly expenditures for its Large Language Model (LLM) API invocations. Analysis indicates that a significant portion (40%) of user queries are straightforward, frequently asked questions (e.g., 'What are your operating hours?') that do not necessitate an LLM's processing. Considering a Databricks-friendly setup, what architectural change would yield the GREATEST cost savings specifically addressing this prevalent query pattern?

  1. AMove the requests from the large general-purpose LLM to a much smaller, cheaper model to reduce the per-token price across the whole workload.
  2. BLower max_tokens for each generation, for example from 1024 to 512, to cut output-token spend while keeping retrieval and prompts unchanged.
  3. CAdd a routing layer that classifies each query and answers simple FAQs from a Delta FAQ table lookup, forwarding the rest to the RAG and LLM flow.
  4. DRaise the retriever's top-k from 5 to 10 so that richer context improves first-pass answers and reduces the number of follow-up turns users need to ask.
Answer & explanation

Correct answer: C

WHY C: Query routing bypasses the LLM entirely for the 40% of queries that are simple FAQs, reducing LLM costs by approximately that proportion. Serving FAQ answers from a cached Delta table or lookup eliminates both prompt and completion tokens for those queries. This is the highest-leverage cost optimization: not calling the LLM at all is always cheaper than calling a smaller or more restricted LLM.

WHY NOT A: Switching to a small model (for example a 7B model) for the whole workload may degrade quality on complex reasoning questions. It also still incurs LLM costs for the 40% of queries that do not need an LLM at all. Routing to no LLM is better than routing to a cheaper LLM for that category.

WHY NOT B: Halving max_tokens reduces output token costs but not input/prompt token costs. For short FAQ answers, output tokens are already low; the input prompt (system prompt + retrieved chunks + user question) dominates the cost. This delivers minimal savings for the FAQ category.

WHY NOT D: Increasing top-k from 5 to 10 doubles the number of retrieved chunks, which increases the prompt token count and therefore increases LLM costs, the opposite of the goal.

Take the full GenAI Engineer practice test free →

Would you pass today?

This question is one of 45 in the free, timed Databricks Generative AI Engineer Associate practice test. Take it and get a section-by-section score.

Start the free test →