AI-900 Practice Question: Describe features of generative AI workloads on Azure
What is prompt engineering?
⚠ Common exam trap
Many exam-takers confuse prompt engineering with model training or fine-tuning, because both involve 'shaping' model behavior, but prompt engineering requires no parameter updates and relies solely on input design.
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
✓
The practice of designing effective inputs to guide AI model outputs
Prompt engineering is the practice of designing and refining input prompts (text instructions) to guide the behavior and output of large language models (LLMs) like GPT-4 or Azure OpenAI. It leverages the model's pre-trained knowledge without modifying its weights, using techniques such as zero-shot, few-shot, or chain-of-thought prompting to achieve desired responses. This is a core skill in generative AI workloads because the quality of the output directly depends on the structure and specificity of the prompt.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
The process of training large language models from scratch
Why it's wrong here
Training a large language model from scratch is a resource-intensive process that gathers a massive corpus, initializes the transformer architecture, and performs billions of gradient updates on GPU/TPU clusters over weeks to learn statistical patterns. Prompt engineering assumes the model has already gone through pretraining, and often supervised fine-tuning and alignment, and simply constructs better input text to elicit knowledge already stored in the weights. It never updates parameters; therefore it is an inference-time technique, not a training methodology.
- ✓
The practice of designing effective inputs to guide AI model outputs
Why this is correct
Prompt engineering is the deliberate, iterative crafting of a generative AI model's textual input—including instructions, role framing, context, and few-shot examples—to steer the probability distribution over the model's outputs toward a desired result. It does not alter the model's weights or training data; instead, it exploits in-context learning and output formatting constraints to improve accuracy, relevance, and safety. This makes it a crucial skill for controlling the behavior of large language models in production.
- ✗
A method of compressing AI models to run on smaller devices
Why it's wrong here
This option describes model optimization techniques such as quantization, pruning, and knowledge distillation, which reduce parameter size and inference latency so models can fit on phones, edge devices, or embedded hardware. Prompt engineering, in contrast, leaves the deployed model untouched and operates entirely at inference time by modifying the user's input text. While both can affect deployment efficiency, compression is a model-level transformation, not an input-design discipline.
- ✗
A way to fix bugs in AI software
Why it's wrong here
Bug fixing is a software development activity that involves diagnosing root causes of erroneous behavior, editing code or configuration, and running regression tests to verify the fix. It changes the program's logic or runtime environment, whereas prompt engineering changes only the natural-language instructions or examples sent to an already-working model. One debug scenario might be when a model's output is nonsensical; a prompt engineer might adjust wording, but fixing the underlying model or application bug requires code-level changes.
Go deeper
Related to this question
Learn chapter
Types of AI Workloads
Key term
Generative AI
Generative AI is a type of artificial intelligence that creates new content—like text, images, or code—by learning patterns from existing data.
Key term
Model
In IT and AI, a model is a trained mathematical representation that learns patterns from data to make predictions or decisions.
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.