AI-102 Exam Overview
Prepare for the Microsoft AI-102 certification exam
with our comprehensive study guide. This study material contains 273 practice questions
sourced from real exams and expert-verified for accuracy. Each question includes the correct answer
and a detailed explanation to help you understand the material thoroughly.
The AI-102 exam — Designing and Implementing a Microsoft Azure AI Solution — is offered by Microsoft.
Passing this exam earns you the Microsoft Certified: Azure AI Engineer Associate credential,
an industry-recognized certification that validates your expertise.
Our study materials were last updated on 2026-02-10 to reflect the
most recent exam objectives and content.
About the Microsoft Certified: Azure AI Engineer Associate
The Microsoft Certified: Azure AI Engineer Associate is awarded by Microsoft
to professionals who demonstrate competence in the skills measured by the AI-102 exam.
According to the
official Microsoft certification page,
this certification validates your ability to work with the technologies covered in the exam objectives.
According to the
Global Knowledge IT Skills and Salary Report,
certified IT professionals earn 15-25% more than their non-certified peers.
Certifications from Microsoft are among the most recognized credentials in the IT industry,
with strong demand across enterprise organizations worldwide.
Free Sample — 15 Practice Questions
Preview 15 of 273 questions from the AI-102 exam.
Try before you buy — purchase the full study guide for all 273 questions with answers and explanations.
Question 2
You have the following Python function.
You call the function by using the following code.
my_function(text_analytics_client, "the quick brown fox jumps over the lazy dog")
Following 'Key phrases', what output will you receive?
A. The quick - The lazy
B. jumps over the
C. quick brown fox lazy dog
D. the quick brown fox jumps over the lazy dog
Show Answer
Correct Answer: C
Explanation:
Azure Text Analytics key phrase extraction removes stop words and returns the most relevant noun phrases rather than full sentences. For the sentence provided, common words like "the" and verbs are dropped, leaving the main content terms: "quick brown fox" and "lazy dog", which together match option C.
Question 3
You are developing a text processing solution.
You have the following function.
You call the function and use the following string as the second argument.
Our tour of London included a visit to Buckingham Palace
What will the function return?
A. London and Buckingham Palace only
B. Tour and visit only
C. London and Tour only
D. Our tour of London included visit to Buckingham Palace
Show Answer
Correct Answer: A
Explanation:
The function uses TextAnalyticsClient.RecognizeEntities to extract named entities (proper nouns such as locations). In the sentence, the recognized entities are the place names "London" and "Buckingham Palace". Common nouns like "tour" and "visit" are not returned, so only those two entities are output.
Question 4
HOTSPOT
-
You have 1,000 scanned images of hand-written survey responses. The surveys do NOT have a consistent layout.
You have an Azure subscription that contains an Azure AI Document Intelligence resource named AIdoc1.
You open Document Intelligence Studio and create a new project.
You need to extract data from the survey responses. The solution must minimize development effort.
To where should you upload the images, and which type of model should you use? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
Show Answer
Correct Answer: Upload to:
An Azure Storage account
Model type:
Custom neural
Explanation:
Document Intelligence Studio uses Azure Storage for uploading and managing large sets of documents with minimal setup. Because the surveys are handwritten and have no consistent layout, a Custom neural model is best suited; it handles unstructured documents and handwriting without requiring fixed templates, minimizing development effort.
Question 5
You have an Azure DevOps pipeline named Pipeline1 that is used to deploy an app. Pipeline1 includes a step that will create an Azure AI services account.
You need to add a step to Pipeline1 that will identify the created Azure AI services account. The solution must minimize development effort.
Which Azure Command-Line Interface (CLI) command should you run?
A. az resource link
B. az cognitiveservices account network-rule
C. az cognitiveservices account show
D. az account list
Show Answer
Correct Answer: C
Explanation:
To identify an Azure AI (Cognitive Services) account created earlier in the pipeline with minimal effort, you should retrieve its details. The `az cognitiveservices account show` command is designed to display information about a specific Cognitive Services account, making it the correct choice. The other options either manage networking, link resources, or list Azure subscriptions rather than identifying a Cognitive Services account.
Question 6
You have an Azure subscription that contains an Azure AI Content Safety resource named CS1.
You plan to build an app that will analyze user-generated documents and identify obscure offensive terms.
You need to create a dictionary that will contain the offensive terms. The solution must minimize development effort.
What should you use?
A. a text classifier
B. language detection
C. text moderation
D. a blocklist
Show Answer
Correct Answer: D
Explanation:
Azure AI Content Safety supports blocklists, which let you define and manage a custom dictionary of offensive or sensitive terms. This directly meets the requirement to identify obscure offensive terms while minimizing development effort, since no custom model training or complex logic is required.
Question 7
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 Safety metaprompt feature to run the tests.
Does this meet the requirement?
Show Answer
Correct Answer: B
Explanation:
The Safety metaprompt feature in Content Safety Studio is used to guide or constrain model behavior with safety instructions, not to test or tune content filter configurations using sample inputs and outputs. Testing and optimizing content filters requires moderation/testing features, not safety metaprompts. Therefore, the solution does not meet the requirement.
Question 8
DRAG DROP
-
You have an Azure subscription that contains an Azure AI Document Intelligence resource named DI1 and a storage account named sa1. The sa1 account contains a blob container named blob1 and an Azure Files share named share1.
You plan to build a custom model named Model1 in DI1.
You create sample forms and JSON files for Model1.
You need to train Model1 and retrieve the ID of the model.
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.
NOTE: More than one order of answer choices is correct. You will receive credit for any of the correct orders you select.
Show Answer
Correct Answer: Upload the forms and JSON files to blob1.
Create a shared access signature (SAS) URL for blob1.
Call the Build model REST API function.
Call the Get model REST API function.
Explanation:
Custom model training in Azure AI Document Intelligence requires training data in an Azure Blob container. A SAS URL grants DI1 access to the blobs. The Build model API trains the model, and the Get model API retrieves the trained model information, including the model ID.
Question 9
HOTSPOT
-
You have an Azure subscription.
You plan to build a solution that will analyze scanned documents and export relevant fields to a database.
You need to recommend an Azure AI Document Intelligence model for the following types of documents:
• Expenditure request authorization forms
• Structured and unstructured survey forms
• Structured employment application forms
The solution must minimize development effort and costs.
Which type of model should you recommend for each document type? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
Show Answer
Correct Answer: Expenditure request authorization forms: Custom template
Structured employment application forms: Prebuilt contract
Structured and unstructured survey forms: Custom neural
Explanation:
Custom template fits repeatable authorization forms with limited training. Prebuilt contract already extracts common applicant-style entities with minimal setup. Custom neural handles mixed structured/unstructured surveys and varying layouts best while avoiding multiple templates.
Question 10
You have an Azure subscription that contains an Azure OpenAI resource named AI1.
You build a chatbot that uses AI1 to provide generative answers to specific questions.
You need to ensure that the chatbot checks all input and output for objectionable content.
Which type of resource should you create first?
A. Microsoft Defender Threat Intelligence (Defender TI)
B. Azure AI Content Safety
C. Log Analytics
D. Azure Machine Leaning
Show Answer
Correct Answer: B
Explanation:
Azure AI Content Safety is specifically designed to analyze and filter both input prompts and AI-generated outputs for harmful, unsafe, or objectionable content. It integrates directly with Azure OpenAI workloads to enforce content moderation policies. The other options do not provide content moderation capabilities for generative AI.
Question 11
You have an Azure subscription and 10,000 ASCII files.
You need to identify files that contain specific phrases. The solution must use cosine similarity.
Which Azure OpenAI model should you use?
A. text-embedding-ada-002
B. GPT-4
C. GPT-35 Turbo
D. GPT-4-32k
Show Answer
Correct Answer: A
Explanation:
The requirement is to identify files containing specific phrases using cosine similarity. Cosine similarity operates on vector embeddings, so an embedding model is required. text-embedding-ada-002 is designed to convert text into numerical vectors optimized for similarity search and semantic matching. GPT-4, GPT-35 Turbo, and GPT-4-32k are generative models, not embedding models, and are not suitable for cosine similarity–based search.
Question 12
You have an Azure subscription.
You need to deploy an Azure AI Search resource that will recognize geographic locations.
Which built-in skill should you include in the skillset for the resource?
A. AzureOpenAIEmbeddingSkill
B. DocumentExtractionSkill
C. EntityRecognitionSkill
D. EntityLinkingSkill
Show Answer
Correct Answer: C
Explanation:
To recognize geographic locations, you need a skill that extracts entities such as locations, people, and organizations from text. The built-in EntityRecognitionSkill is designed for this purpose and supports location (geographic) entities, making it the correct choice.
Question 13
You have an Azure subscription that contains an Azure AI Document Intelligence resource named AIdoc1 in the S0 tier.
You have the files shown in the following table.
You need to train a custom extraction model by using AIdoc1.
Which files can you upload to Document Intelligence Studio?
A. File1, File2, and File4 only
B. File2, and File5 only
C. File2, File4, and File5 only
D. File1, File2, File3, File4, and File5
E. File1 and File2 only
Show Answer
Correct Answer: E
Explanation:
Azure AI Document Intelligence supports image formats (JPG, PNG, TIFF) and PDFs, but not Office files like XLSX. Password-protected PDFs are not supported because the service cannot access encrypted content. For the S0 tier, files up to 500 MB are supported. Therefore:
- File1 (JPG, 400 MB): Supported format and size ✅
- File2 (PDF, 250 MB): Supported format and size ✅
- File3 (PNG, 600 MB): Exceeds 500 MB limit ❌
- File4 (XLSX): Unsupported format ❌
- File5 (Password-protected PDF): Not supported ❌
Thus, only File1 and File2 can be uploaded.
Question 14
You have a local folder that contains the files shown in the following table.
You need to analyze the files by using Azure AI Video Indexer.
Which files can you upload to the Video Indexer website?
A. File1 and File3 only
B. File1, File2, File3 and File4
C. File1, File2, and File3 only
D. File1 and File2 only
E. File1, File2, and File4 only
Show Answer
Correct Answer: B
Explanation:
Azure AI Video Indexer supports WMV, AVI, MOV, and MP4 formats. For uploads from a local device, the size limit is 2 GB and the duration limit is up to 6 hours (360 minutes). All four files are in supported formats, are under 2 GB in size, and have durations within the 6-hour limit, so all can be uploaded.
Question 15
You have an Azure AI Search resource named Search1.
You have an app named App1 that uses Search1 to index content.
You need to add a custom skill to App1 to ensure that the app can recognize and retrieve properties from invoices by using Search1.
What should you include in the solution?
A. Azure AI Immersive Reader
B. Azure OpenAI
C. Azure AI Document Intelligence
D. Azure AI Custom Vision
Show Answer
Correct Answer: C
Explanation:
To recognize and extract structured properties from invoices (such as invoice number, dates, totals, and vendor details) within an Azure AI Search indexing pipeline, you need a service designed for document and form analysis. Azure AI Document Intelligence (formerly Form Recognizer) provides prebuilt invoice models and integrates as a custom skill with Azure AI Search, enabling extraction and indexing of invoice fields for search and retrieval.
Question 16
HOTSPOT
-
You have an Azure subscription that contains an Azure AI Video Indexer account.
You need to add a custom brand and logo to the indexer and configure an exclusion for the custom brand.
How should you complete the REST API call? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
Show Answer
Correct Answer: enabled
false
Explanation:
In Azure AI Video Indexer, the **enabled** property controls inclusion or exclusion. Setting **enabled: false** places the custom brand in the Excluded list so it will not be detected during indexing, which satisfies the requirement to configure an exclusion.