AIF-C01 Fundamentals of Generative AI Practice Question
A company wants to personalize its generative AI model for its specific domain without sharing data with third-party model providers. Which method should they use?
⚠ Common exam trap
AWS often tests the distinction between methods that modify model parameters (fine-tuning) versus those that only augment input or retrieval (prompt engineering, RAG), leading candidates to mistakenly choose RAG for personalization when fine-tuning is required for deep domain adaptation.
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
✓
Fine-tuning the foundation model on their proprietary data
Fine-tuning the foundation model on proprietary data allows the company to adapt the model's weights to its specific domain without sharing data with third parties. This method trains the model on private datasets, enabling it to learn domain-specific patterns and terminology while keeping data in-house, which is critical for data privacy and compliance.
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 their proprietary data
Why this is correct
Fine-tuning adjusts a foundation model's weights using the company's proprietary domain data, and the resulting custom model remains within the organisation's Azure AI resource. No training data is shared with the third-party provider, satisfying the data-confidentiality constraint in the stem.
- ✗
Prompt engineering with domain-specific examples
Why it's wrong here
Prompt engineering supplies context at inference but alters no model parameters, so the model itself remains unpersonalised to the domain and the provider still hosts the same foundation model. It is tempting because it is the fastest, cheapest way to steer outputs using examples, and suits tasks needing only light guidance.
- ✗
Retrieval-augmented generation (RAG) with a domain-specific knowledge base
Why it's wrong here
RAG retrieves from an external knowledge base at inference time; it does not modify the model's weights, so the domain adaptation stays outside the model and the provider relationship is unchanged. It is tempting because RAG is the standard approach for grounding responses in private documents without training.
- ✗
Model distillation using a larger foundation model
Why it's wrong here
Distillation transfers behaviour from a larger teacher model into a smaller student, which requires running the teacher and typically involves the provider's model, contradicting the no-data-sharing constraint. It is tempting because distillation genuinely produces a smaller deployable model, which suits latency and cost reduction rather than domain personalisation.
Go deeper
Related to this question
About these practice questions
Courseiva writes every AIF-C01 question from scratch — 862 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
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.