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

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 < tags > for structure (e.g., < table > , < tr > , < td > ). 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

Microsoft Reference

Common data formats: CSV, JSON, Avro, and Parquet

To prevent an Azure OpenAI model (such as GPT-4 or GPT-3.5) from returning outputs that include hate speech, you must configure Azure AI Content Safety content filters on the model deployment. Content filters evaluate prompts and/or completions for categories like Hate/Unfairness, Harassment/Violence, Sexual, and Self-harm and can block or redact responses when they exceed your selected threshold. Applying a content filter to Model1 ensures that App1 will not return hate speech, satisfying the requirement.

Why the other options are incorrect:

A. Frequency penalty – discourages token/repetition in output; it does not moderate harmful content.

B. Abuse monitoring – provides telemetry/policy monitoring for potential misuse; it is not a response-time content filter and does not block specific hate content.

D. Temperature – adjusts randomness/creativity; it does not enforce safety.

Microsoft Azure AI References

Azure OpenAI Service – Safety system & content filtering (configure per deployment; categories include Hate).

Azure AI Content Safety – Overview and moderation categories.

Azure OpenAI Studio – Attach Content Safety filters to deployments (prompt/completion filtering).

The statement is:

" In an infrastructure as a service (IaaS) instance of Microsoft SQL Server on Azure, you manage the ______ that hosts SQL Server. "

Options:

Elastic pool → A PaaS concept in Azure SQL Database (used to share resources across multiple databases). Not IaaS.

MySQL server → Refers to Azure Database for MySQL (PaaS). Not related to SQL Server on IaaS.

PostgreSQL server → Refers to Azure Database for PostgreSQL (PaaS). Not related to SQL Server on IaaS.

Virtual machine → In IaaS, SQL Server is installed on an Azure VM. You manage the VM (OS, patches, SQL installation, backups, etc.). ✅

Thus, for IaaS, you are responsible for managing the virtual machine that hosts SQL Server.

Correct Answer: virtual machine

Microsoft References

SQL Server on Azure Virtual Machines overview

Compare Azure SQL Database (PaaS) vs SQL Server on VMs (IaaS)

Dialog Recap

The Bot Framework Composer dialog shown:

Bot asks: “What is your name?”

User input stored in user.name .

Property is user.name with a value expression: =coalesce(@user.Name, @personName)

Bot asks: “Hello ${user.name}, how old are you?”

User input stored in user.age .

Statement Analysis

user.name is an entity.

No.

user.name here is not an entity. It is a property in the bot’s memory (user state).

Entities come from LUIS/CLU recognition, while this is a variable property.

The dialog asks for a user name and a user age and assigns appropriate values to the user.name and user.age properties.

Yes.

The dialog explicitly prompts for a text input (name) and a number input (age) and assigns them to user.name and user.age .

The chatbot attempts to take the first non-null entity value for userName or personName and assigns the value to user.name.

Yes.

The expression =coalesce(@user.Name, @personName) ensures that if @user.Name exists, it’s used; otherwise, it tries @personName . This is exactly first-non-null entity resolution.

Final Answer

user.name is an entity. → No

The dialog asks for a user name and a user age and assigns appropriate values to the user.name and user.age properties. → Yes

The chatbot attempts to take the first non-null entity value for userName or personName and assigns the value to user.name. → Yes

Microsoft References

Bot Framework Composer – Memory and Properties

Expressions and coalesce function

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.

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

Microsoft References

Structured, semi-structured, and unstructured data

What is semi-structured data?

Azure Cosmos DB and JSON data model

To “recognize geographic locations” in Azure AI Search enrichment, add the EntityRecognitionSkill to your skillset. This built-in cognitive skill performs named entity recognition (NER) and extracts entities such as locations, people, and organizations from text.

EntityLinkingSkill links already-recognized entities to a knowledge base (e.g., Wikipedia) and is not required just to detect locations.

DocumentExtractionSkill parses file content/structure.

AzureOpenAIEmbeddingSkill creates vector embeddings, not entities.

Microsoft References

Azure AI Search – Entity recognition skill (extracts entities including locations).

Azure AI Search – Entity linking skill (disambiguates entities to a knowledge base; not for initial recognition).

 Stream processing has access to the most recent data received or data within a rolling time window. → Yes

 Batch processing must occur immediately and have latency in the order of seconds or milliseconds. → No

 Stream processing is used for simple response functions, aggregates, or calculations such as rolling averages. → Yes

Comprehensive Detailed Explanation

Stream processing has access to the most recent data received or data within a rolling time window.

Correct.

Stream processing handles real-time or near real-time data.

It operates on a continuous data stream and often uses a rolling time window for analytics.

Answer: Yes

Batch processing must occur immediately and have latency in the order of seconds or milliseconds.

Incorrect.

Batch processing is designed for large volumes of data collected over time.

It typically has high latency (minutes, hours, or even days), not immediate execution.

Answer: No

Stream processing is used for simple response functions, aggregates, or calculations such as rolling averages.

Correct.

Common stream analytics tasks include event-driven responses, real-time aggregations, anomaly detection, and rolling averages.

Answer: Yes

Correct Answers:

Yes

No

Yes

Microsoft References

Batch vs. Stream processing in Azure

Azure Stream Analytics overview

The A in ACID stands for Atomicity .

Atomicity ensures that all parts of a transaction are completed. If any part fails, the entire transaction is rolled back → all-or-nothing execution.

Isolation ensures transactions do not interfere with each other.

Consistency ensures data moves from one valid state to another.

Durability ensures committed changes survive failures.

Correct Answer: B. atomicity

You are building a Text-to-Speech (TTS) solution in Azure Cognitive Services Speech that must:

Convert up to 400 characters (short-form TTS, not long audio synthesis).

Provide multiple voice options to users.

Minimize costs (short-form TTS is cheaper than long-form neural synthesis).

To provide a list of available voices, Azure Speech exposes a REST API endpoint:

Correct endpoint:

https: / / < region > .tts.speech.microsoft.com/cognitiveservices/voices/list

This endpoint returns a list of all available voices (standard + neural) supported in the region, including locale, gender, and style.

Evaluating the Options:

Option A: /longaudiosynthesis/voices

Wrong. This is for long audio synthesis (narration/long documents).

More expensive and not needed for short social media messages.

Option B: /cognitiveservices/voices/list ✅

Correct. This endpoint lists available voices for short-form text-to-speech, which matches the requirements.

Option C: /cognitiveservices/v1?deploymentId={deployment}

Wrong. This is for using a custom voice deployment.

Not required here since the solution should minimize cost and use standard available voices.

Option D: /speechtotext/v3.0/models/base

Wrong. This is for speech-to-text (STT), not text-to-speech.

Correct Answer:

B. https://uksouth.tts.speech.microsoft.com/cognitiveservices/voices/list

Microsoft References

Azure Speech Service REST API reference

List voices in Azure Text-to-Speech

You created five bots with Microsoft Bot Framework Composer, but want to make them appear as one unified bot for users, with dynamic routing depending on user input.

This is exactly the Bot Framework Orchestrator scenario. Orchestrator is the recognizer that allows you to dispatch incoming utterances to the correct skill (bot) or dialog.

Step 1 – Install Orchestrator package

To use Orchestrator inside Bot Framework Composer, you first install the Orchestrator package.

This provides the functionality for language understanding and routing.

Correct answer: F.

Step 2 – Change Recognizer/Dispatch type

By default, a bot project might use LUIS recognizer or Regex recognizer.

To use Orchestrator, you need to change the recognizer type to Orchestrator in Composer.

Correct answer: B.

Step 3 – Create an Orchestrator model

Orchestrator requires a trained model that maps utterances to intents or routes them to the correct skill/bot.

You must create an Orchestrator model for dispatch.

Correct answer: A.

Other Options (Incorrect):

C. Create a Composer extension → Not required for orchestrating multiple bots.

D. Enable WebSockets → Useful for streaming scenarios, not for bot orchestration.

E. Create a custom recognizer JSON file → Applies to building custom recognizers, not needed with Orchestrator.

a tabular form of rows and columns

Rationale

Relational data is, by definition, data that adheres to the relational model .

In the relational model, data is organized into tables , which consist of rows (records or tuples) and columns (fields or attributes). This is known as the tabular form .

The other options are incorrect:

Unstructured data is the opposite of relational data.

A hierarchical folder structure is used for file organization, not the logical structure of relational data.

Comma-separated value (CSV) files can contain relational data, but the core definition of relational data is the tabular structure , not the file format itself.

First blank: speech_recognition_language

Second blank: add_target_language

speech_translation_config = speechsdk.translation.SpeechTranslationConfig(

subscription=os.environ.get( ' SPEECH_KEY ' ),

region=os.environ.get( ' SPEECH_REGION ' )

)

# Source (recognition) language: English (US)

speech_translation_config.speech_recognition_language = " en-US "

# Target translation language: Italian

speech_translation_config.add_target_language( " it " )

audio_config = speechsdk.audio.AudioConfig(use_default_microphone= True )

recognizer = speechsdk.translation.TranslationRecognizer(

translation_config=speech_translation_config,

audio_config=audio_config

)

Comprehensive Detailed Explanation along with All References available from Microsoft Azure AI Solution at the end of the explanation

To translate speech, configure a SpeechTranslationConfig with (1) the recognition language of the input audio and (2) one or more target languages for translation. In Python, you set the input language with the speech_recognition_language property (e.g., " en-US " ), and you add a target with add_target_language( " < locale > " ) (e.g., " it " for Italian). This exactly matches the SDK guidance and examples for speech translation. Microsoft Learn

speech_recognition_language specifies the locale used by the recognizer to understand the spoken input.

add_target_language( " it " ) adds Italian as a translation output language.

Microsoft References

How to translate speech with the Speech SDK (Python examples show translation_config.speech_recognition_language = from_language and translation_config.add_target_language(...) ). Microsoft Learn

SpeechTranslationConfig (Python) reference — add_target_language(language: str) . Microsoft Lea rn

Recognize speech (property usage for speech_recognition_language ). Microsoft Learn

Language support for Speech service (locales and codes for recognition/translation)

The requirement is to extract text from scanned images (OCR at scale).

Computer Vision Image Analysis can describe and tag images but is not optimized for bulk OCR.

Form Recognizer is intended for structured document extraction (invoices, receipts, forms), not raw magazine scans.

Azure Cognitive Service for Language works only with text, not images.

Read API in Computer Vision is specifically designed for extracting text from scanned images, supports multiple languages, and is ideal for this scenario.

Correct Answer: B

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-vision/how-to/call-analyze-image?tabs=version-3-2#analyze-an-image-from-a-stream

Evaluate different models.

The best way to compare the performances of the detection models is to use them on a sample dataset. We recommend calling the Face - Detect API on a variety of images, especially images of many faces or of faces that are difficult to see, using each detection model. Pay attention to the number of faces that each model returns.

You need to restrict access to an Azure AI services (Cognitive Services) account so that only specific resources on a virtual network can reach it and block public (external) access with minimum effort.

The simplest approach is to use Virtual Network service endpoints for Microsoft.CognitiveServices:

Enable the service endpoint on the VNet/subnet (VNet1) for Microsoft.CognitiveServices

This routes traffic from that subnet to the Cognitive Services account over the Azure backbone and allows the account to identify traffic coming from that subnet.

Modify the Cognitive Services account’s network settings (CSAccount1)

Set Public network access: Disabled (or allow access from Selected networks) and add the VNet/subnet enabled with the service endpoint to the allowed list.

This blocks all external access while permitting access from only the specified VNet resources.

Other options are not appropriate:

A. Modify VNet settings (generic) doesn’t target the required service endpoint action.

C. IAM controls user/role authorization, not network access.

D. Create a virtual subnet isn’t necessary if the VNet/subnet already exists; using service endpoints avoids creating/maintaining private endpoints.

Therefore, the correct pair is B and E.

Microsoft Azure AI Solution References

Secure Cognitive Services with virtual network service endpoints – explains enabling Microsoft.CognitiveServices service endpoints on a subnet and restricting the account to selected networks.

https://learn.microsoft.com/azure/ai-services/cognitive-services-virtual-networks

Network access restrictions for Cognitive Services – details configuring “Public network access” and allowing access from selected VNets/subnets.

https://learn.microsoft.com/azure/ai-services/cognitive-services-network-security

Overview of securing Azure AI services – covers options (service endpoints vs. private endpoints) and minimal configuration steps.

https://learn.microsoft.com/azure/ai-services/security-networking

In SQL, commands are categorized into different language groups depending on their purpose:

Data Manipulation Language (DML):

Deals with manipulating the data stored in existing database objects.

Includes:

SELECT → query data

INSERT → add new records

UPDATE → modify existing records

DELETE → remove records

Therefore, UPDATE is a DML statement.

Data Definition Language (DDL):

Used to define and manage database schema objects (tables, indexes, schemas).

Includes: CREATE , ALTER , DROP , TRUNCATE .

Data Control Language (DCL):

Used to control access and permissions.

Includes: GRANT , REVOKE .

Now let’s map the options:

A. REVOKE → DCL (not DML).

B. UPDATE → DML ✅ (correct).

C. DROP → DDL (removes database objects).

D. CREATE → DDL (creates database objects).

Correct Answer: B. UPDATE

Microsoft References

SQL Language Elements – DDL, DML, DCL

UPDATE (Transact-SQL)

Key Knowledge:

To analyze images with Azure OpenAI, you must use a GPT-4 model with vision support (model version vision-preview ).

This requires deploying a GPT-4 model for vision.

Then you use the Chat playground (not completions, not DALL-E) since you want analysis, not generation.

You need to give the assistant instructions in the system message field (e.g., “You are an AI assistant that describes images”).

Finally, you upload an image and prompt the model to describe it.

Correct Sequence:

Create a new deployment, select a GPT-4 model, and set Model version to vision-preview.

Because GPT-4 with vision is required.

Open Chat playground and select the deployed model.

Vision capabilities are accessed through the Chat playground.

In the System message field, enter: “You are an AI assistant that describes images.”

This sets the assistant’s role.

In the Chat session pane, enter a text prompt of “Describe this image,” and upload an image by using the attachment button.

This triggers the model to analyze and describe the image.

Verified Answer (Correct Order):

Create a new deployment, select a GPT-4 model, and set Model version to vision-preview.

Open Chat playground and select the deployed model.

In the System message field, enter: You are an AI assistant that describes images.

In the Chat session pane, enter: Describe this image , and upload an image by using the attachment button.

Microsoft References:

Azure OpenAI vision capabilities

Azure OpenAI Studio overview

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.

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.

Comprehensive Detailed Explanation

The 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]

Microsoft References

Adaptive Cards Templating

Adaptive Card $when property

Multilingual data in Azure Cognitive Search and Adaptive Cards

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.

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.

Box 1: api-nam.cognitive.microsofttranslator.com

https://docs.microsoft.com/en-us/azure/cognitive-services/translator/reference/v3-0-reference

Box 2: /translate

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.

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.

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

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.

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.

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.

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.

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. < field > .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

Microsoft References

Azure AI Document Intelligence – Confidence scores

Human-in-the-loop for Document Intelligence

Your app currently calls the prebuilt Business Card model v2.1. In v2.1, the platform does not provide QR/barcode interpretation. Support for decoding barcodes (including QR codes) was introduced with the v3.x API family as an add-on capability ( ocr.barcode ) that you can enable on analysis requests in API versions 2023-07-31 (GA) and later. Therefore, the first step is to upgrade from v2.1 to v3.0 so your application can use the newer API surface that supports barcode/QR extraction. This meets the “minimize administrative effort” requirement because you keep the same Azure AI Document Intelligence resource, keys, and endpoint—your change is primarily to the API/SDK version and request options.

After upgrading, you have two common implementation patterns:

Continue to use prebuilt Business Card for the contact fields, and in the same flow make an additional call with prebuilt Layout (or General Document) with the ocr.barcode add-on enabled to decode any QR code present on the card. This is the recommended path because the Business Card model itself doesn’t expose add-on features, while the platform’s v3.x analysis APIs do support ocr.barcode on other models. Microsoft Learn

Why the other options are not correct:

A. Deploy a custom model – unnecessary effort; barcode/QR decoding is available out-of-the-box in v3.x via ocr.barcode . Microsoft Learn

B. Implement the read model – Read (OCR) extracts text but does not interpret barcodes/QR codes; you need the barcode add-on introduced in v3.x. Microsoft Learn

D. Implement the contract model – Irrelevant to business cards or QR decoding.

Key Microsoft References

Add-on capabilities (including ocr.barcode with QR support) — available in API 2023-07-31 (GA) and later. Microsoft Learn

Barcode/QR extraction behavior and schema (barcodes collection, kind, value, polygon). Microsoft Learn

Migration guide from v2.1 to v3.x (why upgrade and what changes). Azure Docs

Business Card model documentation and versioning context (v2.1/v3.0/v3.1). Microsoft Learn

SDK/blog announcement of barcode add-on in v3.x (what it returns and when it’s supported). Microsoft for Developers

Code samples showing the barcodes add-on usage. github.com

Platform as a service (PaaS) database offerings in Azure require less setup and configuration effort than Infrastructure as a Service (IaaS) database offerings.

Yes

PaaS abstracts away the OS, patching, backups, and much of the infrastructure management. IaaS requires users to configure and manage VMs and databases manually.

Platform as a service (PaaS) database offerings in Azure provide end users with the ability to control and update the operating system version.

No

In PaaS, the OS and platform management are handled by Azure. Users cannot directly control or update the OS version. This is a responsibility difference between IaaS and PaaS.

All relational and non-relational platform as a service (PaaS) database offerings in Azure can be paused to reduce costs.

No

Not all PaaS database services support pausing. For example, Azure SQL Database serverless can auto-pause, but Azure Cosmos DB and provisioned SQL databases cannot. Hence this statement is incorrect.

Correct Responses:

Yes

No

No

Microsoft References

Azure SQL Database – PaaS overview

What is PaaS?

Serverless compute tier in Azure SQL Database (auto-pause)