AI-102 Designing and Implementing a Microsoft Azure AI Solution Questions and Answers

Conversational Language Understanding (CLU) is trained using utterances.

Adding these example phrases as utterances for the FindContact intent is exactly how training is done.

This ensures the model learns to recognize similar queries.

Correct Answer: Yes

Box 1: QnA Maker Editor

Scenario: Provide all employees with the ability to edit Q&As.

The QnA Maker Editor (read/write) has the following permissions:

Create KB API

Update KB API

Replace KB API

Replace Alterations

"Train API" [in

new service model v5]

Box 2: Contributor

Scenario: Only senior managers must be able to publish updates.

Contributor permission: All except ability to add new members to roles

Parameter type: stream

Visual features list: VisualFeatureTypes.Description

Result to use: results.Description.Captions[0]

To generate accessible alt text, you should use the caption produced by Azure Computer Vision’s Description feature (it produces a human-readable sentence with a confidence score). Therefore:

The image input should be a stream, because you’re uploading images (not just passing URLs) during product creation and AnalyzeImage…Async supports image streams.

Request the Description feature in VisualFeatureTypes so the service returns results.Description.Captions.

Use results.Description.Captions[0] and return the caption text if its confidence is high enough (e.g., > 0.5) to meet the accessibility requirement that all images must have relevant alt text.

Other features (Tags, Objects, Brands) are useful for enrichment but do not directly return natural-language captions suitable for alt text.

Microsoft Azure AI Solution References

Computer Vision (Image Analysis) – Description/Captions and features: Microsoft Docs, Image Analysis – VisualFeatureTypes.Description returns description.captions.https://learn.microsoft.com/azure/ai-services/computer-vision/concept-image-analysis

SDK usage (analyze image from a stream): Microsoft Docs, Analyze an image by using the Computer Vision client library.https://learn.microsoft.com/azure/ai-services/computer-visi on/how-to/call-analyze-image?tabs=version-3-2#analyze-an-image-from-a-stream

The application stores data in a shared folder on a Windows server. The equivalent in Azure Storage is Azure Files, which provides:

Fully managed file shares in the cloud.

Support for the SMB (Server Message Block) protocol, so they can be mounted like traditional shared folders.

Easy migration of on-premises file shares to Azure.

Other storage options:

Table → NoSQL key-value store, not for file shares.

Queue → For message storage and processing, not files.

Blob → For unstructured object storage, but not mountable as a shared drive.

Therefore, Azure File Storage is correct.

Microsoft Reference: Azure Files overview

account

The statement is:

"When provisioning an Azure Cosmos DB ______, you need to specify which type of API you will use."

Options:

account → Correct. When you create a Cosmos DB account, you must choose the API type (e.g., SQL API, MongoDB API, Cassandra API, Table API, Gremlin API). This decision defines the data model and query language. ✅

container → A container is created inside a database (tables, collections, graphs) but does not determine the API type.

database → Exists inside an account and inherits the API type from the account.

item → Represents individual records/documents; not where the API is chosen.

Thus, the API choice is made at the account level.

Correct Answer: account

Azure Cosmos DB account overview

Choose the right API for Cosmos DB

Microsoft References

Step 1: Create a new project and load sample documents

Create a new project. Projects store your configurations and settings.

Step 2: Label the sample documents

When you create or open a project, the main tag editor window opens.

Step 3: Train a custom model.

Finally, train a custom model.

According to the Microsoft documentation, Computer Vision is a cloud-based service that provides developers with access to advanced algorithms for processing images and returning information. By uploading an image or specifying an image URL, Computer Vision algorithms can analyze visual content in different ways based on inputs and user choices.

According to the Microsoft documentation, image type detection is one of the features of Computer Vision that can categorize an image as either a photograph or a drawing. You can use the image type detection feature by calling the Analyze Image API with the visualFeatures parameter set to ImageType. The API will return a JSON response with an imageType field that indicates whether the image is a photo or a clipart.

According to the Microsoft documentation, image descriptions is another feature of Computer Vision that can generate a caption for an image. You can use the image descriptions feature by calling the Analyze Image API with the visualFeatures parameter set to Description. The API will return a JSON response with a description field that contains a list of captions for the image, each with a confidence score.

Therefore, by using these two features of Computer Vision, you can achieve your app requirements with minimal development effort. You don’t need to use any other services, such as object detection, content tags, or Custom Vision, which are designed for different purposes.

Identify the road signs and generate a short description of each road sign: Azure AI Vision is the most suitable choice for this task. It is designed for image analysis and can accurately detect and describe objects such as road signs in large datasets like your 100,000 images. This service is optimized for computer vision tasks and helps minimize costs by efficiently processing images at scale.

Analyze the descriptions to generate a report about the different types of road signs and how often each type occurred: Azure OpenAI GPT-4-Turbo is ideal for this action. It can process natural language descriptions, identify patterns, and generate a detailed report based on the frequency of different road sign types. This model is cost-effective for text analysis tasks and can handle the volume of data derived from the image descriptions while providing advanced language understanding.

Explanation

Semi-structured data

Let’s break down the options:

Graph data

Used in graph databases (e.g., Azure Cosmos DB Gremlin API, Neo4j).

Represents nodes and edges with relationships.

JSON is not graph data.

Relational data

Stored in relational databases with tables, rows, and columns.

JSON does not follow a fixed schema with rows/columns.

Semi-structured data

Correct.

JSON, XML, and Avro are common examples of semi-structured data.

They don’t require a rigid schema like relational data, but still have organizational elements (tags, key-value pairs).

JSON is widely used in NoSQL/document databases like Azure Cosmos DB.

Unstructured data

Examples: images, videos, free text, audio.

JSON does not fit here because it has a defined structure with keys and values.

Correct Answer: Semi-structured data

Structured, semi-structured, and unstructured data

What is semi-structured data?

Azure Cosmos DB and JSON data model

Microsoft References

The requirement is for supporting voice interactions across multiple client apps.

Cortana is deprecated and limited to Cortana channels only.

Microsoft Teams is app-specific and not suited for multiple client apps.

Direct Line Speech is designed to connect bots with Speech SDK-enabled clients, enabling voice-first bots that can work across multiple applications and devices.Therefore, Direct Line Speech is the correct channel.

Step 1: Export the model using the Export for containers (GZIP) option.

Export versioned app's package from LUIS portal

The versioned app's package is available from the Versions list page.

Sign on to the LUIS portal.

Select the app in the list.

Select Manage in the app's navigation bar.

Select Versions in the left navigation bar.

Select the checkbox to the left of the version name in the list.

Select the Export item from the contextual toolbar above the list.

Select Export for container (GZIP).

The package is downloaded from the browser.

Step 2: Select v1.1 of app1.

A trained or published app packaged as a mounted input to the container with its associated App ID.

Step 3: Run a contain and mount the model file.

Run the container, with the required input mount and billing settings.

Comprehensive Detailed ExplanationWhen 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.

Correct Answer: A. Add follow-up prompts

Multi-turn conversations in Question Answering

Add follow-up prompts in Question Answering

Microsoft References

To restrict access so that only resources in vnet1 can access the Language service:

You configure the virtual network settings on the Language service resource.

This enables private endpoint integration with the VNet.

NSGs and Azure Firewall apply to subnets/resources but do not configure the service resource itself.

Containers can run Language service locally but are not needed here.

Correct Answer: C

You need to detect PPE compliance (masks or safety glasses) on a periodic schedule (every 15 minutes) while minimizing development effort and cost.

Why Computer Vision (Azure AI Vision)Azure AI Vision (formerly “Computer Vision”) lets you analyze still images with prebuilt Image Analysis and—when needed—train a lightweight custom object detection model directly in Vision Studio without building ML pipelines. You can simply grab a frame (snapshot) from your camera feed every 15 minutes and call the Vision API—this keeps costs low because you pay per image analyzed rather than continuously processing video. Microsoft’s current Vision stack supports image analysis and custom object detection via Vision Studio and v4.0 APIs, designed for scenarios like PPE detection. Microsoft Azure+1

Why not FaceThe Face service is intended for face detection/recognition workflows. While Face can return some accessory attributes (e.g., glasses/mask confidence), Microsoft has scaled back several face attributes under Responsible AI guidance, and Face is not positioned as a general PPE-compliance detector across a scene (multiple people, full body PPE). It’s therefore a poorer fit and can increase false decisions for PPE checks beyond the face region. Azure Docs+3

Why not Azure Video Analyzer for Media (Video Indexer)Video Indexer is optimized for extracting insights from full videos (speech, people, labels, brands). Running it just to check PPE every 15 minutes is overkill and more expensive than analyzing a single still frame with Vision. In addition, Microsoft has been adjusting video services post–Azure Media Services retirement; using snapshot + Vision avoids those complexities and keeps costs minimal.

How this meets the requirements

Identify masks/safety glasses: Use Image Analysis or a quick custom object detector in Vision Studio trained on a small set of PPE images. Microsoft Learn

Every 15 minutes: Capture a single frame from the camera and call the Vision endpoint—simple scheduling with a timer-triggered Function or Logic App, minimal code. (General Azure pattern; Vision API is stateless per image.) Microsoft Azure

Minimize development effort: Vision Studio provides no-code/low-code training and testing for custom detectors if the prebuilt model isn’t sufficient. Microsoft Learn

Minimize costs: Pay-per-call image analysis is cheaper than indexing entire video segments; no continuous streaming required. Microsoft Azure

Answer: B. Computer Vision

Microsoft References

Azure AI Vision (product overview): image and video analysis with OCR, object detection, Image Analysis. Microsoft Azure

What’s new in Azure AI Vision: custom image classification/object detection in Vision Studio and v4.0 APIs. Microsoft Learn

Face detection & attributes (accessories including glasses and mask)—not the right tool for scene-level PPE compliance. Microsoft Learn

Face Detect REST API (attributes list, including glasses/mask). Microsoft Learn

Responsible AI updates indicating changes to facial analysis attributes; facial detection/accessories remain but are limited in scope. Azure Docs

Azure AI Video Indexer release notes/updates (video-centric use cases, ongoing adjustments post–AMS retirement).

The scenario requires:

An app that uses both Speech and Language APIs.

A single endpoint and single credential for accessing both services.

Let’s analyze the options:

Option A – Azure AI Language

Provides only language-related capabilities (text analytics, QnA, summarization, etc.).

Does not include Speech APIs.

So, this would not meet the requirement.

Option B – Azure AI Foundry service ✅

Previously known as Azure Cognitive Services (multi-service account).

Allows you to provision one unified resource that gives access to multiple Azure AI services (Vision, Speech, Language, Content Safety, etc.).

Provides a single endpoint and single API key/credential across these services.

Perfectly fits the requirement of the question.

Option C – Azure AI Speech

Provides only speech-related capabilities (speech-to-text, text-to-speech, speech translation, speaker recognition).

Does not include Language APIs.

Therefore, not suitable.

Option D – Azure AI Foundry Content Safety

Focused on safety and responsible AI (moderation of text and images).

Does not include general speech or language APIs.

Not applicable here.

Microsoft References

Azure AI Foundry documentation (formerly Cognitive Services)

Azure AI services overview

Provisioning Azure AI services as a single multi-service resource

Comprehensive Detailed ExplanationYou’re adding multiple images for each person into a PersonGroup using the Face API SDK.

File.OpenRead(imagePath) returns a Stream, so the using declaration must declare Stream t = File.OpenRead(imagePath).

To upload an image from a stream to a person in a person group, callfaceClient.PersonGroupPerson.AddFaceFromStreamAsync(personGroupId, personId, t);

Putting it together:

Parallel.For(0, PersonCount, async i =>

{

Guid personId = persons[i].PersonId;

string personImageDir = $"/path/to/person/{i}/images";

foreach (string imagePath in Directory.GetFiles(personImageDir, "*.jpg"))

{

using (Stream t = File.OpenRead(imagePath))

{

await faceClient.PersonGroupPerson.AddFaceFromStreamAsync(

personGroupId, personId, t);

}

}

});

This loops the images for each person, opens each as a stream, and adds the face to the specified person in the person group.

Microsoft Docs – Face API: Add a face to a person (AddFaceFromStreamAsync, AddFaceFromUrlAsync) in PersonGroupPerson operations.https://learn.microsoft.com/azure/ai-services/face/ (see SDK/PersonGroupPerson methods)

.NET File.OpenRead returns Stream.https://learn.microsoft.com/dotnet/api/system.io.file.openread

References

Azure AI Document Intelligence offers pre-built models for common document types like invoices, which extract key fields (e.g., vendor, amount, date) with minimal setup. For custom forms like internal authorization requests, the pre-built general document model handles layout and text extraction, but to minimize development effort, use the pre-built invoice model where applicable and a custom model only if pre-built options fall short. However, the standard recommendation prioritizes pre-built for both to avoid training.

Box 1: Cognitive Service User

Ensure that the members of a group named Management-Accountants can approve the FAQs.

Approve=publish.

Cognitive Service User (read/write/publish): API permissions: All access to Cognitive Services resource except for ability to:

1. Add new members to roles.

2. Create new resources.

Box 2: Cognitive Services QnA Maker Editor

Ensure that the members of a group named Consultant-Accountants can create and amend the FAQs.

QnA Maker Editor: API permissions:

1. Create KB API

2. Update KB API

3. Replace KB API

4. Replace Alterations

5. "Train API" [in new service model v5]

Box 3: Cognitive Services QnA Maker Read

Ensure that the members of a group named the Agent-CustomerServices can browse the FAQs.

QnA Maker Read: API Permissions:

1. Download KB API

2. List KBs for user API

3. Get Knowledge base details

4. Download Alterations

Generate Answer

Explanation:

Scenario: When the response confidence score is low, ensure that the chatbot can provide other response options to the customers.

When no good match is found by the ranker, the confidence score of 0.0 or "None" is returned and the default response is "No good match found in the KB". You can override this default response in the bot or application code calling the endpoint. Alternately, you can also set the override response in Azure and this changes the default for all knowledge bases deployed in a particular QnA Maker service.

Choosing Ranker type: By default, QnA Maker searches through questions and answers. If you want to search through questions only, to generate an answer, use the RankerType=QuestionOnly in the POST body of the GenerateAnswer request.

To mask (redact) phone numbers and email addresses in text using Azure AI Language, you should call the PII entity recognition operation and then print the redacted text that the service returns. In the SDKs, this corresponds to calling RecognizePiiEntities and reading the RedactedText from the result object. The PII feature automatically detects categories such as PhoneNumber and Email and returns a redacted version of the input (masked) in the redactedText/RedactedText field. This is exactly what the code snippet’s “Masked Text” output is asking for.

Therefore:

Use RecognizePiiEntities to detect and redact PII in the document.

Output RedactedText to print the masked string.

Microsoft References

How-to: Detect and redact PII in text (overview and redaction behavior). Microsoft Learn

Quickstart: Detect Personally Identifiable Information (shows PII detection and redacted output). Microsoft Learn

.NET reference: PiiEntityCollection.RedactedText property (“Gets the text of the input document with all PII redacted”). Microsoft Learn

Python client overview: recognize_pii_entities operation for PII detection. Microsoft Learn

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.

The wiki contains text in English, French and Portuguese.

Scenario: All planned projects must support English, French, and Portuguese.

The Document Extraction skill extracts content from a file within the enrichment pipeline. This allows you to take advantage of the document extraction step that normally happens before the skillset execution with files that may be generated by other skills.

Note: The Translator Text API will be used to determine the from language. The Language detection skill is not required.

Can search content in different formats, including video

Audio and video insights (multi-channels). When indexing by one channel, partial result for those models will be available.

Keywords extraction: Extracts keywords from speech and visual text.

Named entities extraction: Extracts brands, locations, and people from speech and visual text via natural language processing (NLP).

Topic inference: Makes inference of main topics from transcripts. The 2nd-level IPTC taxonomy is included.

Artifacts: Extracts rich set of "next level of details" artifacts for each of the models.

Sentiment analysis: Identifies positive, negative, and neutral sentiments from speech and visual text.

C: Analyze Receipt - Get Analyze Receipt Result.

Query the status and retrieve the result of an Analyze Receipt operation.

Request URL: https://{endpoint}/formrecognizer/v2.0-preview/prebuilt/receipt/analyzeResults/{resultId}

E: POST {Endpoint}/vision/v3.2/read/analyze

Use this interface to get the result of a Read operation, employing the state-of-the-art Optical Character Recognition (OCR) algorithms optimized for text-heavy documents.

Scenario: Contoso plans to develop a document processing workflow to extract information automatically from PDFs and images of financial documents

The document processing solution must be able to process standardized financial documents that have the following characteristics:

- Contain fewer than 20 pages.

- Be formatted as PDF or JPEG files.

- Have a distinct standard for each office.

*The document processing solution must be able to extract tables and text from the financial documents.

The document processing solution must be able to extract information from receipt images.

Scenario: All planned projects must support English, French, and Portuguese.

If a bot uses multiple LUIS models and QnA Maker knowledge bases (knowledge bases), you can use the Dispatch tool to determine which LUIS model or QnA Maker knowledge base best matches the user input. The dispatch tool does this by creating a single LUIS app to route user input to the correct model.

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.

The requirements state:

All AI solution responses must have a confidence score ≥ 70%.

If the response confidence score is < 70%, the response must be improved by human input.

Members of the Consultant-Bookkeeper group must be able to process financial documents, which includes performing manual review when the AI confidence is below threshold.

Looking at the provided JSON:

"fields": {

"ReceiptType": {

"type": "string",

"valueString": "Itemized",

"confidence": 0.672

},

"MerchantName": {

"type": "string",

"valueString": "Tailwind",

"confidence": 0.913

}

}

ReceiptType.confidence = 0.672 → this is below 0.7.

MerchantName.confidence = 0.913 → this is above 0.7.

Therefore, the correct condition for triggering manual review is:

documentResults.fields..confidence < 0.7

Now, evaluating the options:

A. documentResults.docType == "prebuilt:receipt"

Always true for receipts, does not check confidence. Not correct.

B. documentResults.fields.*.confidence < 0.7

This is the correct general expression: trigger manual review whenever any field confidence is below 0.7.

C. documentResults.fields.ReceiptType.confidence > 0.7

This would bypass manual review when ReceiptType has high confidence. The requirement is to trigger review when confidence < 0.7, so this is the opposite.

D. documentResults.fields.MerchantName.confidence < 0.7

This only checks one field (MerchantName). In the JSON, MerchantName has confidence 0.913 (>0.7), so this condition would not trigger, but ReceiptType clearly needs review. Too narrow.

Correct Answer: B. documentResults.fields.*.confidence < 0.7

Azure AI Document Intelligence – Confidence scores

Human-in-the-loop for Document Intelligence

Microsoft References

Scenario: Support autocompletion and autosuggestion based on all product name variants.

A: Call a suggester-enabled query, in the form of a Suggestion request or Autocomplete request, using an API. API usage is illustrated in the following call to the Autocomplete REST API.

POST /indexes/myxboxgames/docs/autocomplete?search&api-version=2020-06-30

{

"search": "minecraf",

"suggesterName": "sg"

}

B: In Azure Cognitive Search, typeahead or "search-as-you-type" is enabled through a suggester. A suggester provides a list of fields that undergo additional tokenization, generating prefix sequences to support matches on partial terms. For example, a suggester that includes a City field with a value for "Seattle" will have prefix combinations of "sea", "seat", "seatt", and "seattl" to support typeahead.

F. Use the default standard Lucene analyzer ("analyzer": null) or a language analyzer (for example, "analyzer": "en.Microsoft") on the field.

The given data format is:

FirstName,LastName,Age,LeisureHobby,SportsHobby

John,Smith,23,Reading,Basketball

Ben,Smith,21,Guitar,Curling

This format uses commas to separate fields, with the first row as column headers and subsequent rows as records.

This is the definition of CSV (Comma-Separated Values) format.

Now let’s eliminate the other options:

JSON: Uses { } braces and key-value pairs like "FirstName": "John". Not shown here.

HTML: Uses for structure (e.g.,

, ,

). Not shown here. YAML: Uses indentation and key-value pairs (e.g., FirstName: John). Not shown here. Therefore, the correct format is CSV. Correct Answer: A. CSV Common data formats: CSV, JSON, Avro, and Parquet Microsoft Reference Questions 34 You have a training dataset that contains 10,000 PDF documents. The documents contain scanned books, comics, and magazines. You are building a solution that will use Azure Al and a custom model. You need to train the model by using Language Studio. The solution must meet the following requirements: • Tag each item as a book, comic, or magazine. • Minimize development effort. What should you use? Options: A. a custom extraction model B. a multi label classification project C. a custom named entity recognition (NER) project D. a multi label image classification model Show Answer Buy Now Answer: B Explanation: To tag each document as “book,” “comic,” or “magazine” with minimal development effort in Language Studio, you should use Custom Text Classification. In Language Studio, custom text classification supports two modes: Single-label (multi-class) – one class per document. Multi-label – multiple classes per document. Since the categories appear mutually exclusive, in practice you would configure the project as single-label inside the custom text classification experience. Among the provided options, the only correct Language Studio text-classification choice is “a multi label classification project,” which represents the Custom Text Classification project type (the other options are for different tasks). This approach lets you upload or connect your dataset, label samples in the browser, train, evaluate, and deploy a model with minimal code. Why the other options are not suitable: Custom extraction model (Document Intelligence/Form Recognizer) is for field/key-value extraction, not assigning a document to a category. Custom NER project is for extracting entities (names, numbers, etc.) from text, not whole-document classification. Microsoft Learn Multi-label image classification model belongs to vision tooling (e.g., Custom Vision), not Language Studio, and your requirement is text/document categorization. Microsoft References Custom Text Classification overview (supports single-label and multi-label projects). Microsoft Learn Quickstart: Create and train a custom text classification project in Language Studio. Microsoft Learn Data formats and labeling guidance for custom text classification. Microsoft Learn Custom Named Entity Recognition (for contrast; not used for document tagging). Microsoft Learn Questions 35 You are planning the product creation project. You need to build the REST endpoint to create the multilingual product descriptions. How should you complete the URI? To answer, select the appropriate options in the answer area. NOTE: Each correct selection is worth one point. Options: Show Answer Buy Now Answer: Answer: Explanation: Box 1: api-nam.cognitive.microsofttranslator.com https://docs.microsoft.com/en-us/azure/cognitive-services/translator/referenc e/v3-0-reference Box 2: /translate [Reference:, https://docs.microsoft.com/en-us/azure/cognitive-services/translator/reference/v3-0-translate, , , , ] Questions 36 You are developing the shopping on-the-go project. You need to build the Adaptive Card for the chatbot. How should you complete the code? To answer, select the appropriate options in the answer area. NOTE: Each correct selection is worth one point. Options: Show Answer Buy Now Answer: Answer: Explanation: Comprehensive Detailed ExplanationThe requirement is to build an Adaptive Card for the chatbot that supports multilingual product display and meets accessibility requirements. Product Name Display The product JSON stores localized names like "name": { "en": "...", "es": "...", "pt": "..." }. To dynamically render based on the current language, you must use name[language]. This ensures the product name shown in the card adapts automatically to the user’s preferred language. Stock Level Warning Business rules require warnings when stock is low or out of stock. This means you display the stock warning only when stockLevel is not 'OK'. Therefore, the correct condition is:"$when": "${stockLevel != 'OK'}" Image Alt Text for Accessibility Accessibility requirements specify that all images must have alt text in English, Spanish, and Portuguese. In the product JSON, "alttext" is also localized: "altText": { "en": "Bicycle", "es": "Bicicleta", "pt": "Bicicleta" } To render the correct localized alt text dynamically, use image.altText[language]. Correct Selections: First blank: name[language] Second blank: "$when": "${stockLevel != 'OK'}" Third blank: image.altText[language] Adaptive Cards Templating Adaptive Card $when property Multilingual data in Azure Cognitive Search and Adaptive Cards Microsoft References Questions 37 You are developing the smart e-commerce project. You need to design the skillset to include the contents of PDFs in searches. How should you complete the skillset design diagram? To answer, drag the appropriate services to the correct stages. Each service 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. Options: Show Answer Buy Now Answer: Answer: Explanation: Box 1: Azure Blob storage At the start of the pipeline, you have unstructured text or non-text content (such as images, scanned documents, or JPEG files). Data must exist in an Azure data storage service that can be accessed by an indexer. Box 2: Computer Vision API Scenario: Provide users with the ability to search insight gained from the images, manuals, and videos associated with the products. The Computer Vision Read API is Azure's latest OCR technology (learn what's new) that extracts printed text (in several languages), handwritten text (English only), digits, and currency symbols from images and multi-page PDF documents. Box 3: Translator API Scenario: Product descriptions, transcripts, and all text must be available in English, Spanish, and Portuguese. Box 4: Azure Files Scenario: Store all raw insight data that was generated, so the data can be processed later. [Reference:, https://docs.microsoft.com/en-us/azure/search/cognitive-search-concept-intro, , https://docs.microsoft.com/en-us/azure/cognitive-services/computer-vision/overview-ocr, , , , ] Questions 38 ON NO: 2 DRAG DROP You are planning the product creation project. You need to recommend a process for analyzing videos. 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. (Choose four.) Options: Show Answer Buy Now Answer: Answer: Explanation: Scenario: All videos must have transcripts that are associated to the video and included in product descriptions. Product descriptions, transcripts, and all text must be available in English, Spanish, and Portuguese. Step 1: Upload the video to blob storage Given a video or audio file, the file is first dropped into a Blob Storage. T Step 2: Index the video by using the Video Indexer API. When a video is indexed, Video Indexer produces the JSON content that contains details of the specified video insights. The insights include: transcripts, OCRs, faces, topics, blocks, etc. Step 3: Extract the transcript from the Video Indexer API. Step 4: Translate the transcript by using the Translator API. [ence:, https://azure.microsoft.com/en-us/blog/get-video-insights-in-even-more-languages/, , https://docs.microsoft.com/en-us/azure/media-services/video-indexer/video-indexer-output-json-v2, , , ] Exam Code: AI-102 Exam Name: Designing and Implementing a Microsoft Azure AI Solution Last Update: Nov 3, 2025 Questions: 381 AI-102 PDF $28.5  $94.99 $48  $159.99  Add to Cart AI-102 Testing Engine $33  $109.99 $54  $179.99  Add to Cart AI-102 PDF + Testing Engine $43.5  $144.99  Add to Cart Quick Links Home All Exams Contact us About us Guarantee DMCA & Copyrights Recently New Released Certification Exams PEGACPDC25V1 Nov 3, 2025 RVT_ELEC_01101 Nov 3, 2025 CHRP-KE Nov 3, 2025 TM3 Nov 3, 2025 SOA-C03 Nov 3, 2025 Maryland-Real-Estate-Salesperson Nov 3, 2025 PostgreSQL-Essentials Nov 3, 2025 Security-Operations-Engineer Nov 3, 2025 FSCP Nov 3, 2025 Workday-Pro-HCM-Core Nov 3, 2025 C_BCBTM_2509 Nov 3, 2025 Construction-Manager Nov 3, 2025 PCA Nov 3, 2025 CLT Nov 3, 2025 RCWA Nov 3, 2025 CCDM Nov 3, 2025 ISO-IEC-27001-Foundation Nov 3, 2025 Workday-Pro-HCM-Reporting Nov 3, 2025 Managing-Cloud-Security Nov 3, 2025 CCMP Nov 3, 2025 Site Secure TESTED 03 Nov 2025 Copyright © 2014-2025 ClapGeek. All Rights Reserved