Home / GenAI Engineer practice test / Application Development / Question

Databricks Generative AI Engineer Associate · free practice question

An AI-powered healthcare support system is required to decline specific user requests for individual medical diagnoses, yet simultaneously provide beneficial…

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

Updated November 11, 2026

Application Development

An AI-powered healthcare support system is required to decline specific user requests for individual medical diagnoses, yet simultaneously provide beneficial information for general health education inquiries. What is the OPTIMAL guardrail strategy to achieve this?

  1. AAdd a keyword blocklist that rejects queries containing terms such as diagnosis, symptom or therapy before they reach the model
  2. BAdd an intent classifier that separates personal diagnosis requests from general health questions and routes each differently
  3. CSet max_tokens to 50 on the model's output so that responses are too short to contain a detailed medical assessment of the user
  4. DRetrain the model on data with health-related content removed, so that it lacks the medical knowledge needed to attempt a diagnosis
Answer & explanation

Correct answer: B

WHY B is correct: A classifier-based intent guardrail accurately distinguishes the user's semantic intent — 'I have chest pain, what's wrong with me?' (seeking diagnosis) versus 'How does the heart pump blood?' (seeking general education). This allows the assistant to refuse and redirect diagnosis requests while remaining useful for educational queries.

WHY NOT A: A keyword blocklist is overly broad and brittle. Terms like 'symptoms' or 'treatment' appear in legitimate general health education questions. Blocking on keywords would incorrectly refuse a large proportion of benign queries.

WHY NOT C: A short max_tokens limit prevents detailed responses but does not prevent the model from partially providing a diagnosis within 50 tokens. It also truncates legitimate general health explanations.

WHY NOT D: Removing medical training data degrades the model's ability to answer general health education questions — which is a core use case. This approach is also impractical for foundation models whose pretraining is fixed.

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 →