Microsoft

AI-102 Free Practice Questions — Page 4

Question 22

Note: This question is part of a series of questions that present the same scenario. Each question in the series contains a unique solution that might meet the stated goals. Some question sets might have more than one correct solution, while others might not have a correct solution. After you answer a question in this section, you will NOT be able to return to it. As a result, these questions will not appear in the review screen. You have an Azure subscription that contains an Azure OpenAI resource named AI1 and an Azure AI Content Safety resource named CS1. You build a chatbot that uses AI1 to provide generative answers to specific questions and CS1 to check input and output for objectionable content. You need to optimize the content filter configurations by running tests on sample questions. Solution: From Content Safety Studio, you use the Protected material detection feature to run the tests. Does this meet the requirement?

A. Yes
B. No
Show Answer
Correct Answer: B
Explanation:
Protected material detection in Content Safety Studio is intended to identify copyrighted or other protected content, not to test or optimize filters for objectionable or harmful language. To optimize content filter configurations for chatbot input and output, moderation/text analysis features should be used instead. Therefore, the proposed solution does not meet the requirement.

Question 23

Note: This question is part of a series of questions that present the same scenario. Each question in the series contains a unique solution that might meet the stated goals. Some question sets might have more than one correct solution, while others might not have a correct solution. After you answer a question in this section, you will NOT be able to return to it. As a result, these questions will not appear in the review screen. You have an Azure subscription that contains an Azure OpenAI resource named AI1 and an Azure AI Content Safety resource named CS1. You build a chatbot that uses AI1 to provide generative answers to specific questions and CS1 to check input and output for objectionable content. You need to optimize the content filter configurations by running tests on sample questions. Solution: From Content Safety Studio, you use the Moderate text content feature to run the tests. Does this meet the requirement?

A. Yes
B. No
Show Answer
Correct Answer: A
Explanation:
The Moderate text content feature in Content Safety Studio is specifically intended for testing and evaluating how text is classified for harmful or objectionable content. Using it to run sample questions allows you to validate and optimize content filter configurations for both chatbot input and output, which directly meets the stated requirement.

Question 24

HOTSPOT - You have an Azure subscription that contains an Azure AI Content Safety resource named CS1. You need to call CS1 to identify whether a user request contains hateful language. How should you complete the command? To answer, select the appropriate options in the answer area. NOTE: Each correct selection is worth one point.

Illustration for AI-102 question 24
Show Answer
Correct Answer: contentsafety/ text:analyze
Explanation:
To detect hateful language, the Azure AI Content Safety Text Analyze API is used. The correct REST path is the Content Safety service with the text analysis operation, which evaluates categories like Hate.

Question 25

Note: This question is part of a series of questions that present the same scenario. Each question in the series contains a unique solution that might meet the stated goals. Some question sets might have more than one correct solution, while others might not have a correct solution. After you answer a question in this section, you will NOT be able to return to it. As a result, these questions will not appear in the review screen. You have an Azure subscription that contains an Azure OpenAI resource named AI1 and an Azure AI Content Safety resource named CS1. You build a chatbot that uses AI1 to provide generative answers to specific questions and CS1 to check input and output for objectionable content. You need to optimize the content filter configurations by running tests on sample questions. Solution: From Content Safety Studio, you use the Monitor online activity feature to run the tests. Does this meet the requirement?

A. Yes
B. No
Show Answer
Correct Answer: B
Explanation:
The Monitor online activity feature in Content Safety Studio is intended for observing and analyzing live or deployed traffic, not for running controlled tests on sample questions to tune or optimize content filter configurations. Testing and optimization are done using features such as content moderation testing or evaluation tools, so this solution does not meet the requirement.

Question 26

HOTSPOT - You have an Azure subscription that contains an Azure AI Content Safety resource named CS1. You need to use the SDK to call CS1 to identify requests that contain harmful content. How should you complete the code? To answer, select the appropriate options in the answer area. NOTE: Each correct selection is worth one point.

Illustration for AI-102 question 26
Show Answer
Correct Answer: ContentSafetyClient AnalyzeTextOptions
Explanation:
The Azure AI Content Safety SDK uses ContentSafetyClient to connect to the resource, and AnalyzeTextOptions to submit text for harmful content analysis via AnalyzeText.

Question 27

You have an Azure OpenAI model. You have 500 prompt-completion pairs that will be used as training data to fine-tune the model. You need to prepare the training data. Which format should you use for the training data file?

A. CSV
B. XML
C. JSONL
D. TSV
Show Answer
Correct Answer: C
Explanation:
Azure OpenAI fine-tuning requires training data to be provided in JSONL (JSON Lines) format, where each line contains a single prompt–completion pair as a JSON object. This is the supported and documented format for fine-tuning datasets.

Question 29

HOTSPOT - You have an Azure subscription that contains an Azure AI Document Intelligence resource named DI1. You build an app named App1 that analyzes PDF files for handwritten content by using DI1. You need to ensure that App1 will recognize the handwritten content. How should you complete the code? To answer, select the appropriate options in the answer area. NOTE: Each correct selection is worth one point.

Illustration for AI-102 question 29
Show Answer
Correct Answer: prebuilt-read 0.75
Explanation:
The prebuilt-read model is designed for OCR and supports handwritten text recognition. Checking style.is_handwritten with a confidence threshold of 0.75 reliably identifies handwritten content while reducing false positives.

Question 30

You have an Azure subscription that contains an Azure AI Document Intelligence resource named DI1. DI1 uses the Standard S0 pricing tier. You have the files shown in the following table. Which files can you analyze by using DI1?

A. File 1.pdf only
B. File2.jpg only
C. File3.tiff only
D. File2.jpg and File3.tiff only
E. File1.pdf, File2.jpg, and File3.tiff
Show Answer
Correct Answer: C
Explanation:
In the Standard (S0) tier of Azure AI Document Intelligence, PDFs have strict size limits that File1.pdf (800 MB) exceeds, so it cannot be analyzed. Image inputs must meet minimum dimension requirements (at least 50 × 50 pixels). File2.jpg is only 25 × 25 pixels, so it is too small and is not supported. File3.tiff (5 MB, 5000 × 5000 pixels) is within both the size and resolution limits, so it can be analyzed.

Question 31

DRAG DROP - You have an Azure subscription that contains a storage account named sa1 and an Azure AI Document Intelligence resource named DI1. You need to create and train a custom model in DI1 by using Document Intelligence Studio. The solution must minimize development effort. Which four actions should you perform in sequence? To answer, move the appropriate actions from the list of actions to the answer area and arrange them in the correct order.

Illustration for AI-102 question 31
Show Answer
Correct Answer: Create a custom model project and link the project to sa1. Upload five sample documents. Apply labels to the sample documents. Train and test the model.
Explanation:
In Document Intelligence Studio, you first create a custom model project and link it to the storage account to define the workspace. Then upload a small set of sample documents (five) to minimize effort, apply labels for a labeled custom model, and finally train and test the model.

Question 32

HOTSPOT - You are building an app that will provide users with definitions of common AI terms. You create the following Python code. For each of the following statements, select Yes if the statement is true. Otherwise, select No. NOTE: Each correct selection is worth one point.

Illustration for AI-102 question 32 Illustration for AI-102 question 32
Show Answer
Correct Answer: No Yes Yes
Explanation:
1) The model may explain LLMs but does not guarantee a high degree of certainty. 2) Adding context to the question improves clarity and yields the intended definition. 3) A more restrictive system prompt effectively constrains the response to AI language models.

$19

Get all 278 questions with detailed answers and explanations

  • Instant download HTML + PDF delivered the moment payment clears.
  • Secure Stripe checkout we never see or store your card details.
  • 7-day refund if files are defective see our refund policy.