AI-900 Practice Question: Describe features of generative AI workloads on Azure
A company wants to use Azure OpenAI to generate personalized marketing emails. They have a large dataset of customer purchase histories. They want the model to generate emails that recommend products based on individual customer preferences without retraining the entire model. Which technique should they use?
⚠ Common exam trap
Watch out — candidates often confuse fine-tuning with prompt engineering, assuming that any customization requires retraining, when in fact few-shot learning can achieve personalization without modifying model weights.
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
✓
Prompt engineering with few-shot learning
Prompt engineering with few-shot learning is correct because it allows the model to generate personalized marketing emails by providing a few examples of customer-product pairs in the prompt, without modifying the underlying model weights. This technique leverages the pre-trained knowledge of Azure OpenAI to recommend products based on individual customer purchase histories, avoiding the need for costly 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
Why it's wrong here
Supervised fine-tuning updates Azure OpenAI model weights on a curated dataset, requiring significant compute, labeled examples, and a deployment pipeline. Since personalized marketing emails depend on each customer's current attributes, that dynamic context belongs in the prompt at inference time, not baked into permanently modified weights. Re-training or updating the fine-tuned model for every customer segment would be wasteful and doesn't leverage the model's in-context learning ability.
- ✓
Prompt engineering with few-shot learning
Why this is correct
Prompt engineering with few-shot learning places several worked examples of customer attributes mapped to polished marketing emails inside the prompt, then appends the current customer's data as the new query. The model uses in-context learning to mimic the demonstrated style and personalization pattern without any retraining, making it fast and cost-effective for per-customer generation. It directly satisfies the need to incorporate existing customer data as context in the inference call.
- ✗
Reinforcement learning from human feedback
Why it's wrong here
Reinforcement learning from human feedback (RLHF) is a training-time process that uses a reward model and proximal policy optimization to align a model's general behavior with human preferences, not to bind responses to individual business records. It consumes a large fixed preference dataset and permanently changes model weights, so it cannot condition one inference call on a specific customer's name, purchase history, or preferences. Invoking RLHF here conflates model alignment with per-instance grounding, which is exactly what few-shot prompting provides.
- ✗
Creating a custom neural network
Why it's wrong here
Creating a custom neural network from scratch entails defining a new architecture, gathering a massive domain-specific corpus, and running expensive distributed training—neither of which is provided by the Azure OpenAI service. Even if feasible, such a model would start without the broad language understanding the pre-trained GPT model already has, and it would still need per-customer conditioning. Replacing a managed pre-trained LLM with a bespoke network is far more complex than the stated task requires.
Go deeper
Related to this question
Learn chapter
Machine Learning Core Concepts
Key term
Model
In IT and AI, a model is a trained mathematical representation that learns patterns from data to make predictions or decisions.
Key term
Prompt engineering
Prompt engineering is the practice of designing and refining input queries to AI models to get the most accurate, relevant, and useful outputs.
About these practice questions
This AI-900 question is part of Courseiva's 985-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 by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This AI-900 practice question is part of Courseiva's free Microsoft 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 AI-900 exam.