Microsoft Designing and Implementing a Microsoft Azure AI Solution AI-102 Exam Dumps: Updated Questions & Answers (December 2025)

In Custom Question Answering (part of Azure AI Language), if you want to define alternative words or spellings for a specific term (e.g., testing, trials, evaluate), you must use the alterations property.

Each alteration object contains a list of alternative values for the same meaning.

Example:

{

"alterations": [

{

"alterations": [

"testing",

"trials",

"evaluate"

]

}

]

}

phrases is used for pattern matching in question-answer pairs.

synonyms is used for synonyms within LUIS (Language Understanding), not for QnA alterations.

value is used inside synonyms definitions in some contexts but not here.

Correct JSON Payload Completion:The JSON should be:

{

"alterations": [

{

"alterations": [

"testing",

"trials",

"evaluate"

]

}

]

}

Verified Answer:

Left box: "alterations"

Right box: "alterations"

Microsoft References:

Manage alterations in Custom Question Answering (Azure AI Language)

Authoring API reference for alterations

Comprehensive Detailed ExplanationTo move a Question Answering project to a different Azure region, you migrate the project data and then re-deploy it in the target region:

Export the existing project (source region).In Language Studio (Question Answering), you first export the project. This produces a package (JSON/ZIP) containing your knowledge bases, sources, synonyms, and settings. Exporting is the supported way to move a project between resources/regions.

Import the project into the new Language service instance (target region).In the target region’s Language service instance, use Language Studio to import the previously exported file. This recreates the project (KBs and configuration) under the new resource.

Train and publish from the new instance.After import, you must train (build) and then publish the project so that an endpoint is created under the new regional resource. Clients can then point to the new endpoint and key.

Actions like “enable custom text classification” or “regenerate the keys” are not required for moving a Question Answering project, and training/publishing from the original instance won’t deploy to the target region.

Microsoft Azure AI Solution References

Export and import Question Answering projects in Language Studio (move between resources/regions):Microsoft Learn – Export and import projects (Question Answering).https://learn.microsoft.com/azure/ai-services/language-service/question-answering/how-to/export-import-project

Train and publish a Question Answering project:Microsoft Learn – Create, train, and publish projects (Question Answering).https://learn.microsoft.com/azure/ai-services/language-service/question-answering/how-to/create-test-deploy

Language service overview and regional deployment concepts:Microsoft Learn – What is Azure AI Language?https://learn.microsoft.com/azure/ai-services/language-service/overview

An ML entity can be composed of smaller sub-entities, each of which can have its own properties. For example, Address could have the following structure:

Address: 4567 Main Street, NY, 98052, USA

Building Number: 4567

Street Name: Main Street

State: NY

Zip Code: 98052

Country: USA

https://docs.microsoft.com/en-us/azure/cognitive-services/luis/luis-concept-entity-types

The provided code uses the Azure AI Language – Text Analytics client to call the ExtractKeyPhrases method.

The method ExtractKeyPhrases(text) identifies the most important words and phrases in the input text.

The input string is:

"the quick brown fox jumps over the lazy dog"

The ExtractKeyPhrases API removes stopwords such as "the," "over," and "jumps" and extracts only meaningful keywords.

Therefore, the returned list of key phrases will include:

"Quick brown fox"

"Lazy dog"

When printed, the console output after "Key phrases:" will show:

Quick brown fox

Lazy dog

This matches option C (Quick brown fox lazy dog), since the key phrases are concatenated as output lines.

Correct Answer: C. Quick brown fox lazy dog

Azure AI Language – Key phrase extraction

TextAnalyticsClient.ExtractKeyPhrases method (Azure.AI.TextAnalytics)

Microsoft References

Instead, you could migrate to a Cognitive Search service that uses a higher tier.

Note: A simple fix to most throttling issues is to throw more resources at the search service (typically replicas for query-based throttling, or partitions for indexing-based throttling). However, increasing replicas or partitions adds cost, which is why it is important to know the reason why throttling is occurring at all.

The question describes:

An Azure subscription with an Azure AI Content Safety resource.

A social media application where users can upload images.

The requirement is to moderate inappropriate content in those uploaded images.

In Azure AI Content Safety SDKs:

You create a ContentSafetyClient by providing the endpoint and key.

The ContentSafetyClient exposes methods such as:

AnalyzeText() → For text moderation

AnalyzeImage() → For image moderation

Let’s review the code structure:

public static void Analyze(AnalyzeImageOptions request)

{

var endpoint = Environment.GetEnvironmentVariable("ENDPOINT");

var key = Environment.GetEnvironmentVariable("KEY");

var client = new ContentSafetyClient(new Uri(endpoint), new AzureKeyCredential(key));

return client.AnalyzeImage(request);

}

First dropdown: must be ContentSafetyClient to instantiate the correct client for Azure AI Content Safety.

Second dropdown: since the requirement is image moderation, we must call client.AnalyzeImage(request).

Other options:

BlocklistClient → used for custom blocklists, not full moderation.

TextCategoriesAnalysis → refers to text analysis categories, not suitable here.

AnalyzeText → would be used only for text moderation.

Therefore, the correct completion is:

ContentSafetyClient

client.AnalyzeImage(request)

Correct Answer:

First dropdown: ContentSafetyClient

Second dropdown: client.AnalyzeImage(request)

Azure AI Content Safety – Analyze images

Azure AI Content Safety SDK documentation

ContentSafetyClient class

Microsoft References

The requirement is:

Bot asks for a date input.

Bot repeats the question until a valid date is provided.

Bot allows cancellation of transaction.

This is exactly what Prompts in Bot Framework are designed for.

Example: DateTimePrompt asks for a date, validates the input, and automatically re-prompts if invalid.

Waterfall is for multi-step dialog flows, but the specific requirement is repeating until valid input — handled by Prompts.

Adaptive and Action dialogs are not relevant here in SDK context.

Correct Answer: A

The requirement is to allow User1 to add custom data sources to an Azure OpenAI resource (AI1).

Following the principle of least privilege means granting only the specific rights required.

The Cognitive Services OpenAI Contributor role allows management of Azure OpenAI resources, including attaching custom data sources for RAG (retrieval-augmented generation).

The Cognitive Services Contributor role is broader and grants access to all cognitive services, which violates least privilege.

Search Service Contributor and Search Index Data Contributor are roles for Azure AI Search, not for managing data sources on Azure OpenAI.

Microsoft References:

Azure built-in roles: Cognitive Services OpenAI Contributor

The interface must collect structured input: start date, end date, PTO days.

A waterfall dialog is designed for step-by-step data gathering. Each step asks one question and collects one piece of information, minimizing complexity.

Skill dialog is for invoking another bot.

Adaptive dialog handles interruptions and dynamic flow (more complex).

Component dialog organizes dialogs but does not simplify sequential data collection.

Correct Answer: B

Comprehensive Detailed ExplanationIn the Microsoft Bot Framework Composer, there are four main property scopes for storing variables or properties:

dialog scope

Lives only for the lifetime of the dialog.

Once the dialog ends, properties stored in the dialog scope are automatically cleared.

Best suited for temporary values such as user inputs collected during a dialog, like “name” in this case.

user scope

Persists across all conversations with the user.

Data stored here remains available even after dialogs end, making it unsuitable if you want to dispose of the property at the end of the dialog.

conversation scope

Persists throughout the lifetime of a single conversation (from start to end).

Useful for maintaining state across multiple dialogs in the same conversation, but still not automatically disposed of when a dialog ends.

turn (curn in the options is likely a typo)

Lives only for a single turn (a single exchange of user and bot messages).

Cleared at the end of the turn, which is too short-lived for this requirement.

Requirement: “Ensure that you can dispose of the property when the last active dialog ends.”

That means the property should exist only during the dialog execution and then be discarded.

Correct scope for this scenario is dialog.

Applying to the Question

Correct Answer: A. dialog

Manage properties in Bot Framework Composer

Scopes in Bot Framework Composer

Bot Framework Composer memory model

Microsoft References