What is the purpose of 'few-shot prompting'?

To reduce the cost of API calls

To limit the number of tokens in the response

To provide examples in the prompt to guide the model's response

To increase the model's creativity

A developer is using Azure OpenAI to generate code snippets. The model sometimes outputs code with security vulnerabilities. Which prompt engineering technique should they use to reduce this risk?

Use a different model without any prompt changes

Use a larger max_tokens to allow more code

Include security guidelines and examples of secure code in the prompt

Set temperature to 0.0 to make outputs deterministic

A healthcare company wants to fine-tune a generative model to summarize medical reports. They have a dataset of summaries created by doctors. What should they do to ensure the fine-tuned model performs well?

Set temperature to 0.9 during training

Deploy the model immediately after training

Use the entire dataset for training without validation

Split the dataset into training and validation sets and monitor performance during fine-tuning

What is the primary purpose of fine-tuning a generative AI model?

To make the model run on edge devices

To increase the model's maximum token limit

To reduce the model's inference latency

To adapt the model to a specific domain or task using additional training data

Microsoft Certified:Azure AI Engineer Associate

Domain 2Objective 3

Optimize and Operationalize a Generative AI Solution AI-102 Practice Questions (Page 5)

Part of the Implement generative AI solutions domain, which accounts for 15-20% of the AI-102 exam. Microsoft does not publish an official question count, but from its 100-minute exam (~40–65 total, ~6–13 in this domain), expect 2–4 from this objective — we provide 47 practice questions to prepare you well beyond it. (estimate)

47questions here

10free pages

9concepts

15-20%of the exam

Questions 21–25

21foundation · easy
What is the purpose of 'few-shot prompting'?
Select an answer first
22foundation · easy
When configuring a generative AI model for a chat completion task, which parameter directly controls the randomness and diversity of the generated text?
Select an answer first
23application · medium
A developer is using Azure OpenAI to generate code snippets. The model sometimes outputs code with security vulnerabilities. Which prompt engineering technique should they use to reduce this risk?
Select an answer first
24application · medium
A healthcare company wants to fine-tune a generative model to summarize medical reports. They have a dataset of summaries created by doctors. What should they do to ensure the fine-tuned model performs well?
Select an answer first
25foundation · easy
What is the primary purpose of fine-tuning a generative AI model?
Select an answer first

Finished these 5 questions?

Review the revealed explanations, or continue through the curriculum.

Next 5 questions →Back to AI-102

Free Basic Practice is a study aid with revealable answers — not a scored exam. Examers.io is independent and not affiliated with or endorsed by Microsoft. “AI-102” is a trademark of its owner, used for identification only.