Updated Aug-2026 Official licence for AI-102 Certified by AI-102 Dumps PDF
Grab latest Amazon AI-102 Dumps as PDF Updated on 2026
Microsoft AI-102 (Designing and Implementing a Microsoft Azure AI Solution) is a certification exam that aims to test candidates' knowledge and skills in designing and implementing AI solutions using Microsoft Azure. Designing and Implementing a Microsoft Azure AI Solution certification is intended for professionals who have experience working with Microsoft Azure and are looking to enhance their expertise in AI technologies. Successful completion of this certification exam can lead to career advancement opportunities and recognition as an expert in the field of AI.
Topics Covered
Exam AI-102 contains five topics each of which is intended to check specific skills.
1. Plan and Manage an Azure Cognitive Services Solution
This topic implies your ability to choose the suitable Cognitive Services resource, create it, plan and design security for a Cognitive Services solution, and apply Cognitive Services containers. This means that you should be competent in selecting the appropriate cognitive service for solutions that refer to language analysis, speech, decision support, and vision. You also should possess skills to operate costs of Cognitive Services, create a Cognitive Services resource, and monitor a cognitive service. This part also checks how well you can operate Cognitive Services account keys, and protect Cognitive Services. Your knowledge of using Face API, Computer Vision, Speech, Text Analysis, and ability to integrate Cognitive Services Containers in Microsoft Azure will also be assessed.
2. Implement Computer Vision Solutions
The second topic is designed to check your skills in using the Computer Vision API to get image descriptions, define landmarks, find brands, edit content in images, and create thumbnails. In this part, you are expected to be able to detect faces and recognize them in images, analyze facial features, and match similar faces with the help of the Face API. Being competent in utilizing the Custom Vision service, you should demonstrate your skills in applying image classification and implementing an object detection solution. Besides, your ability to analyze video by implementing Azure Video Analyzer for Media will be measured.
3. Implement Natural Language Processing Solutions
In the third topic, candidates are required to show their skills in analyzing text by utilizing the Text Analytics service, control speech by implementing the Speech service, translate the text with the help of the Translator service. This domain also checks your proficiency in creating and optimizing an initial language model by utilizing LUIS, and finally, managing it.
4. Implement Knowledge Mining Solutions
In this domain, you will be required to have expertise related to applying a Cognitive Search solution, which implies creating data sources, identifying an index, running an indexer, and using synonyms. This topic also aims to evaluate your ability to apply an enrichment pipeline, use a knowledge store, operate a Cognitive Search solution and indexing.
5. Implement Conversational AI Solutions
This domain will evaluate your capacity in utilizing QnA Maker to make a knowledge base, creating and implementing conversation flow, creating a bot by utilizing either the Bot Framework Composer or the Bot Framework SDK. Finally, you will need to demonstrate your skills in integrating Cognitive Services into a bot.
NEW QUESTION # 227
You successfully run the following HTTP request.
POST https://management.azure.com/subscriptions/18c51a87-3a69-47a8-aedc-a54745f708a1/resourceGroups
/RG1/providers/Microsoft.CognitiveServices/accounts/contosol/regenerateKey?api-version=2017-04-18 Body{ " keyName " : " Key2 " } What is the result of the request?
- A. A new query key was generated.
- B. A key for Azure Cognitive Services was generated in Azure Key Vault.
- C. The secondary subscription key was reset.
- D. The primary subscription key and the secondary subscription key were rotated.
Answer: C
Explanation:
The HTTP request provided is:
POST https://management.azure.com/subscriptions/18c51a87-3a69-47a8-aedc- a54745f708a1/resourceGroups
/RG1/providers/Microsoft.CognitiveServices/accounts/contosol/regenerateKey?api-version=2017-04-18 Body { " keyName " : " Key2 " }
* The request is made against the Azure Cognitive Services Management API ( Microsoft.
CognitiveServices/accounts/.../regenerateKey ).
* The regenerateKey operation is specifically designed to regenerate one of the two subscription keys used to authenticate Cognitive Services API calls.
* Cognitive Services resources always have two keys: Key1 (primary) and Key2 (secondary).
* This design allows key rotation without downtime: you can regenerate one key while using the other in production.
Key Observations: Body Payload: { " keyName " : " Key2 " }
* This explicitly tells Azure to regenerate Key2 (the secondary subscription key).
* After the call, the secondary subscription key value changes, while Key1 (primary) remains unaffected.
* A. A key for Azure Cognitive Services was generated in Azure Key Vault
* Incorrect. The operation is not integrated with Key Vault; it only regenerates Cognitive Services subscription keys.
* B. A new query key was generated
* Incorrect. Query keys are related to Azure Cognitive Search (not general Cognitive Services).
* The request clearly targets CognitiveServices/accounts.
* C. The primary subscription key and the secondary subscription key were rotated
* Incorrect. The request regenerates only the specified key, not both.
* D. The secondary subscription key was reset
* Correct. The payload specifies " Key2 " , so only the secondary subscription key is regenerated.
Option Analysis
The Answer: D. The secondary subscription key was reset
* Azure REST API - Cognitive Services regenerate key
* Authenticate requests to Azure AI services with keys and endpoint
* Manage Cognitive Services keys (key1/key2)
Microsoft References
NEW QUESTION # 228
You are reviewing the design of a chatbot. The chatbot includes a language generation file that contains the following fragment.
# Greet(user)
- ${Greeting()}, ${user.name}
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth one point.
Answer:
Explanation:
Explanation:
Box 1: No
Example: Greet a user whose name is stored in `user.name`
- ${ welcomeUser(user.name) }
Example: Greet a user whose name you don't know:
- ${ welcomeUser() }
Box 2: No
Greet(User) is a Send a response action.
Box 3: Yes
Reference:
https://docs.microsoft.com/en-us/composer/how-to-ask-for-user-input
NEW QUESTION # 229
You are building a call handling system that will receive calls from French-speaking and German-speaking callers. The system must perform the following tasks;
* Capture inbound voice messages as text.
* Replay messages in English on demand.
Which Azure Cognitive Services should you use? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
Answer:
Explanation:
Explanation
NEW QUESTION # 230
You are building a chatbot.
You need to configure the chatbot to query a knowledge base.
Which dialog class should you use?
- A. AdaptiveDialog
- B. ComponentDialog
- C. SkillDialog
- D. QnAMakerDialog
Answer: D
Explanation:
* If a chatbot must query a knowledge base (KB), the Bot Framework uses QnAMakerDialog (inherited into Azure Cognitive Service for Language's Question Answering).
* AdaptiveDialog manages complex dialog flows but not specifically KB querying.
* ComponentDialog organizes dialogs, but again, not specific for knowledge bases.
* SkillDialog is used when invoking another bot (skill), not for KB queries.
Comprehensive Detailed ExplanationCorrect Answer: B. QnAMakerDialog
Reference: Use QnAMakerDialog in Bot Framework
NEW QUESTION # 231
You are building a chatbot by using the Microsoft Bot Framework Composer. You have the dialog design shown in the following exhibit.
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection Is worth one point.
Answer:
Explanation:
NEW QUESTION # 232
You have a Language Understanding solution that runs in a Docker container.
You download the Language Understanding container image from the Microsoft Container Registry (MCR).
You need to deploy the container image to a host computer.
Which three 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.
Answer:
Explanation:
Explanation:
You are deploying a Language Understanding (LUIS) container. When running LUIS in Docker, the model must first be exported from the Language Understanding portal, and then provided to the container at runtime.
Step-by-step reasoning:
* From the Language Understanding portal, export the solution as a package file.
* The trained LUIS model must be exported from the portal into a .json package file.
* This is required because the container cannot access the hosted service directly.
* From the host computer, move the package file to the Docker input directory.
* Containers expect the model to be available locally.
* The package file is placed into the input directory that the container maps for models.
* From the host computer, run the container and specify the input directory.
* When starting the container, you specify --volume < local_input > :/input so the container has access to the package file.
* This makes the exported model available inside the container for processing.
Why not the other options?
* Retain the model in the portal is not sufficient; the container cannot pull directly from the cloud.
* Build the container and specify the output directory is not required; the container image is already available from MCR and is not custom-built for this step.
Correct Answer Order:
* Export the solution as a package file.
* Move the package file to the Docker input directory.
* Run the container and specify the input directory.
* Run LUIS containers
* Use containers with Azure AI services
Microsoft References
NEW QUESTION # 233
You have a computer that contains the files shown in the following table.
Which files can you upload and analyze by using Azure Al Video Indexer?
- A. File3only
- B. File1, File2, File3, and File4
- C. File1 andFile3 only
- D. File1, File2, and File3 only
- E. File1 only
Answer: C
Explanation:
Azure AI Video Indexer (VI) imposes limits on both file duration and file size:
* Duration: Up to 6 hours for all presets; Basic Audio preset supports up to 12 hours.
* Size: When uploading from your device, the limit is 2 GB (uploading by URL allows up to 30 GB).
* Formats: MP4, AVI (video) and MP3 (audio codec/file) are supported.
Evaluating each file:
* File1 - MP4, 34 mins, 1,500 MB: Within 6-hour duration and under 2 GB # Supported.
* File2 - AVI, 500 mins (#8h20m), 1,700 MB: Exceeds the 6-hour limit # Not supported.
* File3 - MP3, 300 mins (5h), 980 MB: Under 6 hours (and also under the 12-hour Basic Audio limit) and under 2 GB # Supported.
* File4 - MP4, 350 mins (#5h50m), 2,800 MB: Duration is under 6 hours but size exceeds 2 GB for device uploads # Not supported (unless uploaded by URL, which the question doesn't state).
Therefore, the files you can upload and analyze (under standard device upload constraints) are File1 and File3 only.
Microsoft References
* Support matrix & limits - file duration (6h for all presets; 12h for Basic Audio), device upload size limit 2 GB; supported formats (MP4, AVI, WAV, etc.) and audio codecs including MP3. Microsoft Learn
* Release notes - increase of duration limit from 4h to 6h (and 12h for Basic Audio). Microsoft Learn
* Upload guidance - device upload 2 GB vs 30 GB via URL.
NEW QUESTION # 234
You are building an Azure AI Language Understanding solution.
You discover that many intents have similar utterances containing airport names or airport codes.
You need to minimize the number of utterances used to train the model.
Which type of custom entity should you use?
- A. machine-learning
- B. Pattern.any
- C. regular expression
- D. list
Answer: B
Explanation:
https://learn.microsoft.com/en-us/azure/ai-services/luis/concepts/patterns-features#patternany- entity
NEW QUESTION # 235
You have a chatbot.
You need to test the bot by using the Bot Framework Emulator. The solution must ensure that you are prompted for credentials when you sign in to the bot.
Which three settings should you configure? To answer, select the appropriate settings in the answer area.
NOTE Each correct selection is worth one point.
Answer:
Explanation:
Explanation:
When testing a bot with the Bot Framework Emulator, especially if the bot uses authentication (OAuth), you need the Emulator to mimic real-world authentication flows. To do that:
* Use version 1.0 authentication tokens
* Ensures that authentication tokens are generated in the same format as Bot Framework v1.0, which is compatible with most OAuth flows.
* Use a sign-in verification code for OAuthCard
* Prompts the user with a verification code during sign-in flows, ensuring the emulator behaves like a real client app (e.g., mobile or Teams).
* This is required to test sign-in prompts and enforce credential entry.
* Use your own user ID to communicate with the bot
* Ensures that the Emulator identifies you uniquely and triggers authentication properly.
* Without this, the bot may treat sessions generically, and authentication prompts might not behave as expected.
Why not the others?
* Application Updates (automatically download/install) # Related to emulator updates, not authentication.
* Data Collection # Only for telemetry; does not affect authentication.
* Ngrok settings # Used for tunneling remote bot connections; unrelated to credential prompts.
Correct Answer Selections:
* Use version 1.0 authentication tokens
* Use a sign-in verification code for OAuthCard
* Use your own user ID to communicate with the bot
* Bot Framework Emulator - Authentication
* Testing bots with Bot Framework Emulator
Microsoft References
NEW QUESTION # 236
Which scenario is an example of a streaming workload?
- A. sending transactions that are older than a month to an archive
- B. sending cloud infrastructure metadata every 30 minutes
- C. sending telemetry data from edge devices
- D. sending transactions daily from point of sale (POS) devices
Answer: C
Explanation:
* A streaming workload means data is generated continuously and ingested in near real time.
* Telemetry from edge/IoT devices is a classic example of streaming workloads because the devices constantly push data (sensor readings, logs, metrics).
* A. sending transactions daily # batch workload (not streaming).
* B. sending metadata every 30 minutes # periodic batch, not continuous streaming.
* C. sending old transactions to archive # cold data archival, not streaming.
Reference: Azure Stream Analytics overview
NEW QUESTION # 237
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. EntityRecognitionSkill
- B. AzureOpenAIEmbeddingSkill
- C. EntityLinkingSkill
- D. DocumentExtractionSkill
Answer: A
Explanation:
The EntityRecognitionSkill in Azure AI Search is a built-in skill designed to identify and recognize specific types of entities within text, including geographic locations (such as cities, countries, and landmarks), as well as other entities like people and organizations. This makes it the appropriate choice for a skillset intended to recognize geographic locations.
NEW QUESTION # 238
You are developing the knowledgebase by using Azure Cognitive Search.
You need to build a skill that will be used by indexers.
How should you complete the code? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
Answer:
Explanation:
Explanation
Box 1: "categories": ["Locations", "Persons", "Organizations"],
Locations, Persons, Organizations are in the outputs.
Scenario: Contoso plans to develop a searchable knowledgebase of all the intellectual property Note: The categories parameter is an array of categories that should be extracted. Possible category types:
"Person", "Location", "Organization", "Quantity", "Datetime", "URL", "Email". If no category is provided, all types are returned.
Box 2: {"name": " entities"}
The include wikis, so should include entities in the outputs.
Note: entities is an array of complex types that contains rich information about the entities extracted from text, with the following fields name (the actual entity name. This represents a "normalized" form) wikipediaId wikipediaLanguage wikipediaUrl (a link to Wikipedia page for the entity) etc.
Reference:
https://docs.microsoft.com/en-us/azure/search/cognitive-search-skill-entity-recognition
NEW QUESTION # 239
You are developing a call to the Face API. The call must find similar faces from an existing list named employeefaces. The employeefaces list contains 60,000 images.
How should you complete the body of the HTTP request? To answer, drag the appropriate values to the correct targets. Each value may be used once, more than once, or not at all. You may need to drag the split bar between panes or scroll to view content.
NOTE: Each correct selection is worth one point.
Answer:
Explanation:
Explanation
Box 1: LargeFaceListID
LargeFaceList: Add a face to a specified large face list, up to 1,000,000 faces.
Note: Given query face's faceId, to search the similar-looking faces from a faceId array, a face list or a large face list. A "faceListId" is created by FaceList - Create containing persistedFaceIds that will not expire. And a
"largeFaceListId" is created by LargeFaceList - Create containing persistedFaceIds that will also not expire.
Reference:
https://docs.microsoft.com/en-us/rest/api/faceapi/face/findsimilar
NEW QUESTION # 240
You have a flow that you plan to deploy to Azure Machine Learning managed online endpoints for real-time inference.
You need to modify the YAML configuration file for the deployment to ensure that trace data and system metrics are collected and sent to an Application Insights resource named my-app-insights.
How should you modify the file? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
Answer:
Explanation:
Explanation:
NEW QUESTION # 241
You need to implement a table projection to generate a physical expression of an Azure Cognitive Search index.
Which three properties should you specify in the skillset definition JSON configuration table node? Each correct answer presents part of the solution. (Choose three.) NOTE: Each correct selection is worth one point.
- A. dataSourceConnection
- B. dataSource
- C. generatedKeyName
- D. source
- E. tableName
Answer: C,D,E
Explanation:
Defining a table projection.
Each table requires three properties:
tableName: The name of the table in Azure Storage.
generatedKeyName: The column name for the key that uniquely identifies this row.
source: The node from the enrichment tree you are sourcing your enrichments from. This node is usually the output of a shaper, but could be the output of any of the skills.
Reference:
https://docs.microsoft.com/en-us/azure/search/knowledge-store-projection-overview
NEW QUESTION # 242
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth one point.
Answer:
Explanation:
Explanation
NEW QUESTION # 243
You are developing the knowledgebase by using Azure Cognitive Search.
You need to meet the knowledgebase requirements for searching equivalent terms.
What should you include in the solution?
- A. a synonym map
- B. a built-in key phrase extraction skill
- C. a custom analyzer
- D. a suggester
Answer: A
Explanation:
Within a search service, synonym maps are a global resource that associate equivalent terms, expanding the scope of a query without the user having to actually provide the term. For example, assuming "dog", "canine", and "puppy" are mapped synonyms, a query on "canine" will match on a document containing "dog".
Create synonyms: A synonym map is an asset that can be created once and used by many indexes.
Reference:
https://docs.microsoft.com/en-us/azure/search/search-synonyms
NEW QUESTION # 244
You are building a customer support chatbot.
You need to configure the bot to identify the following:
* Code names for internal product development
* Messages that include credit card numbers
The solution must minimize development effort.
Which Azure Cognitive Service for Language feature should you use for each requirement? To answer, drag the appropriate features to the correct requirements. Each feature may be used once, more than once, or not at all. You may need to drag the split bar between panes or scroll to view content NOTE: Each correct selection is worth one point.
Answer:
Explanation:
NEW QUESTION # 245
You are developing an application that will recognize faults in components produced on a factory production line. The components are specific to your business.
You need to use the Custom Vision API to help detect common faults.
Which three 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.
Answer:
Explanation:
Explanation
Graphical user interface, text, application, chat or text message Description automatically generated
Step 1: Create a project
Create a new project.
Step 2: Upload and tag the images
Choose training images. Then upload and tag the images.
Step 3: Train the classifier model.
Train the classifier
Reference:
https://docs.microsoft.com/en-us/azure/cognitive-services/custom-vision-service/getting-started-build-a-classifie
NEW QUESTION # 246
You develop a custom question answering project in Azure Cognitive Service for Language. The project will be used by a chatbot. You need to configure the project to engage in multi-turn conversations. What should you do?
- A. Enable chit-chat.
- B. Add alternate questions.
- C. Add follow-up prompts.
- D. Enable active learning.
Answer: C
Explanation:
When you develop a custom question answering project (formerly QnA Maker, now part of Azure Cognitive Service for Language - Question Answering), you can configure it for multi-turn conversations.
* Follow-up prompts
* Used to create multi-turn conversations.
* They allow the system to present additional questions to the user after an initial question, guiding the conversation flow.
* Example:
* User: "Tell me about Azure Storage."
* Bot: "Which type of storage: Blob, File, Queue, or Table?"
* These follow-up options are configured using follow-up prompts.
* Correct choice for this question.
* Active learning
* Helps improve the knowledge base by suggesting alternative questions from user queries.
* Not related to multi-turn conversation flow.
* Alternate questions
* Used to add different phrasings for the same question.
* Example: "What is Azure Blob Storage?" and "Explain Blob Storage in Azure."
* This improves recognition but does not enable multi-turn conversations.
* Chit-chat
* Adds small talk and casual conversation handling (e.g., greetings, jokes).
* Not related to multi-turn Q&A about a knowledge base.
The answer: A. Add follow-up prompts
* Multi-turn conversations in Question Answering
* Add follow-up prompts in Question Answering
NEW QUESTION # 247
You develop a test method to verify the results retrieved from a call to the Computer Vision API. The call is used to analyze the existence of company logos in images. The call returns a collection of brands named brands.
You have the following code segment.
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth one point.
Answer:
Explanation:
Explanation:
* Query successful
An analysis of the provided code segment is needed to determine the truth value of the statements, which are not explicitly provided in the prompt. Since I don't have the statements, I will analyze the code and infer common types of questions related to this code structure to provide a helpful response.
The code segment is written in a C#-like syntax and iterates through a collection named brands.
C#
foreach (var brand in brands)
{
if (brand.Confidence >= .75)
Console.WriteLine($"Logo of {brand.Name} between {brand.Rectangle.X}, {brand.Rectangle.Y} and {brand.
Rectangle.W}, {brand.Rectangle.H}");
}
* Iteration: The foreach (var brand in brands) loop processes each item (presumably a detected brand or logo) in the brands collection.
* Filtering/Condition: The if (brand.Confidence >= .75) statement acts as a filter. It only processes a brand if its associated Confidence value (likely a floating-point number between 0.0 and 1.0) is greater than or equal to 0.75.
* Output: For brands that pass the confidence threshold, a line of text is printed to the console using string interpolation ($"").
* It reports the Name of the brand.
* It reports the bounding box coordinates, presumably X (horizontal position), Y (vertical position), W (width), and H (height), which are properties of the nested brand.Rectangle object.
NEW QUESTION # 248
Drag and Drop Question
You are building a phone call handling solution that will use the Azure AI Speech service and a custom neural voice.
You need to create a custom speech model.
Which five actions should you perform in sequence from Speech Studio? To answer, move the appropriate actions from the list of actions to the answer area and arrange them in the correct order.
Answer:
Explanation:
Explanation:
Reference:
https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-custom-speech-create- project
https://learn.microsoft.com/en-us/azure/ai-services/speech-service/professional-voice-create- consent
NEW QUESTION # 249
......
For candidates that are aiming to develop their skills in building, operating, and deploying AI solutions with the help of such services as Azure Applied AI services and Azure Cognitive Services, the best variant is to pass the Microsoft AI-102 exam. This exam is all about designing and applying a Microsoft Azure AI Solution, and leads to getting the Microsoft Certified: Azure AI Engineer Associate certification.
Passing this exam implies that certified candidates are able to participate in all stages of AI solutions development from defining requirements to performance tuning and monitoring. These professionals cooperate with solution architects, as well as with data engineers and scientists, AI developers to show their vision and create comprehensive AI solutions.
Latest AI-102 Exam Dumps Microsoft Exam from Training: https://www.passsureexam.com/AI-102-pass4sure-exam-dumps.html
Newly Released AI-102 Dumps for Azure AI Engineer Associate Certified: https://drive.google.com/open?id=1lggOM7ZB79182iuet8yLO-sLtebGqRGz