AIF-C01 Fundamentals of Generative AI Practice Question
A hospital's IT team wants a generative AI assistant that answers patient-billing questions using only the hospital's internal policy documents, without retraining the model. Which approach should they use?
⚠ Common exam trap
The trap here is assuming that instructing a model to stay on topic is equivalent to giving it the source material it needs to answer accurately.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Retrieval Augmented Generation (RAG) by querying a vector store of the policy documents and passing retrieved passages to the model
Retrieval Augmented Generation supplies the model with relevant, current policy text at query time, so responses are grounded in the hospital's own documents. Fine-tuning changes model weights and needs retraining, temperature alters sampling randomness, and a system prompt alone provides no source content. Only retrieval of the policy passages gives accurate, updatable answers without retraining.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Fine-tuning the foundation model on the full set of policy documents
Why it's wrong here
Fine-tuning updates model weights and requires a labeled training dataset and compute time, which contradicts the stated goal of not retraining. It also bakes static knowledge into the model, so policy updates would require another training job, making it a poor fit for frequently revised billing policies.
- ✗
Increasing the model's temperature setting so it explores more of its pretrained knowledge
Why it's wrong here
Temperature controls randomness in token sampling; raising it makes output more varied and less deterministic, not more grounded in hospital policy. It cannot inject private document content into the model, so billing answers would remain based on pretraining data and could be confidently wrong.
- ✓
Retrieval Augmented Generation (RAG) by querying a vector store of the policy documents and passing retrieved passages to the model
Why this is correct
RAG retrieves relevant passages from an external knowledge source at inference time and includes them in the prompt, so the model grounds its answer in the hospital's own policies without any weight updates. This directly satisfies the requirement to avoid retraining while keeping answers tied to authoritative internal documents.
- ✗
Prepending a system instruction telling the model to answer only from hospital policy
Why it's wrong here
A system instruction shapes behavior but does not supply the policy content itself. Without the actual documents in context, the model has no access to the specific billing rules and can still fabricate details, so this alone does not meet the grounding requirement.
Go deeper
Related to this question
About these practice questions
This AIF-C01 question is part of Courseiva's 862-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Amazon Web Services exam blueprint
This AIF-C01 practice question is part of Courseiva's free Amazon Web Services certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AIF-C01 exam.