AI-102 Questions and Answers

Change Domains to General (compact).

Retain the model.

Export the model.

Comprehensive Detailed ExplanationYou have a Custom Vision project that performs object detection. The project currently uses the General domain. You need to export the trained model for offline use (on a disconnected network).

Steps required:

Change Domains to General (compact).

Export is only supported with a Compact domain.

The General (compact) domain is optimized for exporting to devices (e.g., ONNX, TensorFlow, CoreML, etc.).

If you stay in “General” domain, you cannot export.

Retain the model.

After switching domains, you must retrain the model in the new compact domain to generate updated weights.

Export the model.

Once retrained in a compact domain, you can export the model for offline deployment.

Export formats include ONNX, TensorFlow, CoreML, or Docker container, depending on use case.

Create a new classification model → Not needed; you already have an object detection model.

Change the classification type → Incorrect; the problem is with the domain type, not classification type.

Why not the others?

Change Domains to General (compact).

Retain the model.

Export the model.

Correct Answer Order:

Export a model from Custom Vision

Domains in Custom Vision

Microsoft References

Comprehensive Detailed ExplanationThe question focuses on monitoring a public-facing sales system that processes video and text, ensuring that the system provides equitable results regardless of user location or background.

Two Microsoft Responsible AI principles apply directly here:

Fairness

AI systems should treat all people fairly and avoid bias.

Monitoring ensures that outcomes do not disadvantage people based on location, background, or demographics.

This directly addresses the requirement for equitable results.

Inclusiveness

AI systems should empower everyone and engage people of all backgrounds.

Monitoring for inclusiveness ensures that the system works well across different regions, languages, and cultures, making the system accessible and beneficial for all users.

A. Transparency

Important for explaining how AI systems work, but does not directly address equitable results across demographics.

D. Reliability and safety

Focuses on consistent and safe system operation, not equity across users.

E. Privacy and security

Critical for data protection, but not related to equitable treatment of users.

Why not the other options?

Correct Answer:

B. fairness

C. inclusiveness

Microsoft Responsible AI Principles

Fairness in AI systems

Inclusiveness in AI systems

Microsoft References

Paginated reports are designed for printing or PDF generation, with table-style reports that span multiple pages.

These are built using Power BI Report Builder, a standalone tool.

B. Charticulator is for creating custom visuals, not paginated reports.

C. Power BI Desktop builds interactive reports, dashboards, and data models, not paginated reports.

D. Power BI Service is for publishing, sharing, and consuming reports, but not building paginated reports.

Correct Answer: A. Power BI Report Builder

In Power BI, reports are interactive, visual, and support KPIs, drill-through, and drill-down functionality.

Power Apps is for app development, not analytics.

A view is a database object, not a visualization solution.

Dataflow is for ETL/ELT (data preparation), not reporting.

Correct Answer: A

When many utterances differ only by airport names or codes, you don’t want to list them all.

A Pattern.any entity acts as a placeholder for free-form input inside patterns, allowing the model to accept any word/phrase in that slot.

Machine-learning entities require lots of labeled utterances.

List entities work for fixed sets (e.g., specific known airport codes), but this scenario implies dynamic airport data.

Regex entities are for structured formats (like postal codes).

Correct Answer: A

Comprehensive Detailed Explanation

When an indexer runs in Azure AI Search, it processes each document through a fixed series of stages:

Document crackingThe indexer opens the item (file/row) and extracts text, images, and metadata, creating the root of the enriched document (/document). This is always the first stage.

Field mappingsNext, source fields are mapped directly to target index fields before any transformations. Field mappings occur after document cracking but before skillset execution. Microsoft Learn

Skillset executionBuilt-in or custom skills (for example, language and sentiment analysis in your scenario) run and write outputs into the in-memory enriched document. Microsoft Learn

Output field mappingsBecause skill outputs live only in memory, you must define output field mappings to route selected nodes of the enriched document into index fields. This step comes after skillset execution.

Push to indexFinally, the indexer hands off raw and enriched content to the search index (the physical data structures) so it becomes searchable—i.e., the content is “pushed to the index.” Microsoft Learn

This order—document cracking → field mappings → skillset execution → output field mappings → push to index—ensures raw content is extracted, direct source-to-index mappings are applied, AI enrichment is performed, enriched outputs are projected to fields, and the completed documents are written into the index.

Microsoft Azure AI References

Indexers in Azure AI Search – Stages of indexing (Document cracking; Field mappings; Skillset execution; Output field mappings, with field mappings occurring before transformations). Microsoft Learn

Skillset concepts (Output of skillset is routed to the index via output field mappings after skillset execution). Microsoft Learn

AI enrichment concepts (Field mappings move raw source content to the index; output field mappings move enriched content; indexing ingests raw and enriched content into the physical index). Microsoft Learn

Annotations & enriched document tree (Enriched document is created during document cracking at /document). Microsoft Learn

The requirement is to extract structured information (invoice items, sales amounts, customer details) from scanned invoice images.

Form Recognizer (now part of Azure AI Document Intelligence) is specifically designed for extracting structured data from documents such as invoices, receipts, and business forms.

Custom Vision → used for image classification or object detection, not for text/data extraction.

Computer Vision → can extract text with OCR, but it doesn’t provide structured field-level extraction for invoices.

Immersive Reader → for accessibility (reading content aloud, translating text), not document data extraction.

Correct Answer: D

You need to monitor a video stream while ensuring the microphone stays enabled and detect when the user asks a question. The simplest/lowest-effort approach is to use Azure AI Speech-to-text to transcribe the user’s audio in real time, then apply a lightweight check (e.g., interrogatives like “who/what/how” or final “?”) to detect a question. Object detection or the Face service analyze visual content (objects/faces/emotions) and cannot tell whether a spoken utterance is a question. Language detection only identifies which language is being spoken; it does not transcribe or classify questions.

References

Azure AI Speech: real-time speech-to-text (streaming) for transcription and downstream analysis.https://learn.microsoft.com/azure/ai-services/speech-service/speech-to-text

Face service overview (not for speech/question detection).https://learn.microsoft.com/azure/ai-services/computer-vision/overview-identity

Custom Vision object detection overview (visual objects, not spoken questions).https://learn.microsoft.com/azure/ai-services/custom-vision-service/object-detection-overview

Language detection capability description (identifies language only).https://learn.microsoft.com/azure/ai-services/language-service/language-detection/overview

Comprehensive Detailed ExplanationYou are working with a custom question answering project in Azure AI Language (formerly QnA Maker). The requirement is to enable the chatbot to engage in multi-turn conversations.

Multi-turn conversation: This occurs when a bot needs to ask clarifying questions or present follow-up options to guide the user toward the right answer.

Now let’s evaluate the options:

A. Add alternate questions

Alternate questions help improve query matching by allowing different phrasings of the same question.

This does not enable multi-turn dialogue.

B. Enable chit-chat

Chit-chat adds conversational personality (e.g., greetings, small talk).

Useful for user engagement but not for structured multi-turn dialogues.

C. Add follow-up prompts ✅

Follow-up prompts allow you to define next-step questions after an answer.

They are the key mechanism in custom question answering to enable multi-turn conversation flows.

Example: If the answer is about "subscriptions," the follow-up prompts might include "How to upgrade?" or "How to cancel?"

D. Enable active learning

Active learning helps improve accuracy by suggesting alternative phrasing for questions based on user feedback.

This is for model refinement, not multi-turn conversation.

Thus, the correct way to configure the project for multi-turn conversations is to add follow-up prompts.

Correct Answer: C. Add follow-up prompts

Custom question answering in Azure AI Language – Multi-turn conversations

Custom question answering overview

Microsoft References

semi-structured data

The statement is:

"Varying fields for each entity in a JSON document is an example of ______."

Relational data → Stored in structured tables with fixed schema (e.g., SQL database). Not applicable here.

Structured data → Has a strict schema (columns and types are predefined). JSON allows variation, so not structured.

Semi-structured data → Data that does not require a fixed schema, but still uses markers (tags, keys) to separate elements. JSON and XML are classic examples. ✅

Unstructured data → Data without schema or labeling (e.g., videos, images, free text). Not JSON.

Since JSON documents can have varying fields per entity (flexible schema), this is considered semi-structured data.

Correct Answer: semi-structured data

Structured, semi-structured, and unstructured data

JSON in Azure

Microsoft References

Language Understanding: An AI service that allows users to interact with your applications, bots, and IoT devices by using natural language.

QnA Maker is a cloud-based Natural Language Processing (NLP) service that allows you to create a natural conversational layer over your data. It is used to find the most appropriate answer for any input from your custom knowledge base (KB) of information.

Text Analytics: Mine insights in unstructured text using natural language processing (NLP)—no machine learning expertise required. Gain a deeper understanding of customer opinions with sentiment analysis. The Language Detection feature of the Azure Text Analytics REST API evaluates text input

The scenario:

You are building an in-vehicle application that uses Azure AI Speech for text-to-speech (TTS).

Requirement: Optimize the quality of synthesized voice output.

You must choose the most appropriate SSML (Speech Synthesis Markup Language) attribute.

Used to apply expressive styles like "cheerful," "empathetic," or "angry."

Helpful for emotion/tone, but not specifically about audio quality for clarity in motor vehicles.

Controls how strongly certain words are emphasized.

Improves meaning and focus, but does not optimize overall voice quality.

The element allows adjustments to pitch, rate, and volume.

Adjusting pitch directly affects the naturalness and clarity of the synthesized speech.

Especially useful in noisy environments such as cars, because modifying pitch can make speech stand out better against background noise.

This directly improves perceived quality of voice output.

Used for special voice effects (like whispering).

Not typically used for general clarity or quality improvements.

Option A – style attribute of the mstts:express-as elementOption B – level attribute of the emphasis elementOption C – pitch attribute of the prosody element ✅Option D – effect attribute of the voice element

Correct Answer: C. the pitch attribute of the prosody element

SSML support in Azure AI Speech

Prosody element in SSML

Microsoft References

You might want to manage the translation and localization for the language understanding content for your bot independently.

Translate command in the @microsoft/bf-lu library takes advantage of the Microsoft text translation API to automatically machine translate .lu files to one or more than 60+ languages supported by the Microsoft text translation cognitive service.

What is translated?

An .lu file and optionally translate Comments in the lu file

LU reference link texts

List of .lu files under a specific path.

You are building an application that:

Uses Azure Translator service to translate text.

The text comes from getTextToBeTranslated().

The text can be in many languages.

Requirement: the content must remain within the Americas Azure geography.

Output: must translate text into a single language (English in this case).

The Translator service provides region-specific endpoints.

For Americas geography, you must use the North America (NAM) endpoint:

https://api-nam.cognitive.microsofttranslator.com/translate

Other options like api-apc (Asia Pacific) or api-nam.../detect are incorrect because:

/detect is used to identify the source language, not translate.

/transliterate is for script conversion, not translation.

We need the /translate path.

Step 1 – Choosing the correct endpoint

To specify the target language, you must use the to query string parameter. Example:

?to=en

Options like from=en or suggestedFrom=en are not correct here, because:

The text can be in many languages → we don’t know the source language in advance.

Translator automatically detects the source if from is not specified.

We only need to define the target language.

Step 2 – Setting the correct query parameter

Final Code Snippet (corrected)var endpoint = "https://api-nam.cognitive.microsofttranslator.com/translate ";

var apiKey = "YOUR_SUBSCRIPTION_KEY";

var text = getTextToBeTranslated();

var body = "[{'Text':'" + text + "'}]";

var client = new HttpClient();

client.DefaultRequestHeaders.Add("Ocp-Apim-Subscription-Key", apiKey);

var uri = endpoint + "?to=en";

HttpResponseMessage response;

var content = new StringContent(body, Encoding.UTF8, "application/json");

response = await client.PutAsync(uri, content);

Endpoint: https://api-nam.cognitive.microsofttranslator.com/translate

URI: ?to=en

Correct Answer

Translator v3.0 Reference

Region-specific Translator endpoints

Microsoft References

To let an Azure AI Agent access publicly available, recent web content, you add the Bing grounding tool. In the SDK, you first define a ToolConnectionList with the Bing connection ID (here, "bingConnectionId"), then construct a BingGroundingToolDefinition(connectionList) so the agent can call Bing Search with recency filters (e.g., last 90 days) when answering questions.

When creating the agent, tool definitions are passed via the tools: parameter of CreateAgentAsync(...) as a List. The toolResources parameter is used when you must also supply resource descriptors (for example, an Azure AI Search index configuration), which is not needed here because the Bing grounding tool already references the connection through the ToolConnectionList.

Therefore:

Use BingGroundingToolDefinition to ground the agent on current public web data.

Provide that tool in tools: new List { grounding } when calling CreateAgentAsync(...).

Microsoft Azure AI References (titles only)

Azure AI Agent Service – Bing web grounding tool (tool definitions and connections)

Azure AI Agent Service SDK – Agent creation (CreateAgentAsync parameters: tools vs toolResources)

Azure AI Agent Service – Tool connections and ToolConnectionList usage

The Cognitive Services OpenAI User role grants least-privilege read/use permissions: view resource endpoints, list available models, use existing deployments in Azure OpenAI Studio (e.g., generate text and images). It cannot create or manage deployments (that would require Cognitive Services OpenAI Contributor), satisfying least-privilege.

References

Azure OpenAI built-in roles: OpenAI User vs OpenAI Contributor.https://learn.microsoft.com/azu re/ai-services/openai/how-to/role-based-access-control

Azure RBAC for Azure AI services.https://learn.microsoft.com/azure/ai-services/role-based-access-control?tabs=azure-portal

The output will include the following words: our and included. → No

The output will include the following words: Paris, Eiffel, and Tower. → Yes

The function will output all the key phrases from the input string to the console. → No

Comprehensive Detailed ExplanationLet’s examine the function:

static void GetKeyWords(TextAnalyticsClient textAnalyticsClient, string text)

{

var response = textAnalyticsClient.RecognizeEntities(text);

Console.WriteLine("Key words:");

foreach (CategorizedEntity entity in response.Value)

{

Console.WriteLine($"{entity.Text}");

}

}

The function uses RecognizeEntities from the Azure Text Analytics SDK.

RecognizeEntities detects and categorizes named entities in text (such as locations, people, organizations, dates, etc.).

It does not extract all words or key phrases.

For extracting key phrases, you would use ExtractKeyPhrases, not RecognizeEntities.

"The output will include the following words: our and included."

These are common words, not entities. They will not appear.

Answer: No

"The output will include the following words: Paris, Eiffel, and Tower."

These are named entities (location, landmark). They will be recognized and returned.

Answer: Yes

"The function will output all the key phrases from the input string to the console."

No. The function extracts entities, not key phrases. Key phrases would require ExtractKeyPhrases.

Answer: No

Evaluating the statements:

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

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

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.

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.

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

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

This is because the Azure Video Indexer website allows you to upload videos from a URL or from your file system, but there are some limitations and considerations for each option1.

If you upload from your file system, the size of the file is limited to 2 GB, which is less than the size of file1.avi (20 GB). Therefore, this option is not feasible.

If you upload from a URL, the size of the file is limited to 30 GB, which is enough for file1.avi. However, the URL must be publicly accessible and valid, and the file must be accessible. You cannot use URLs from streaming services such as YouTube1. Therefore, options A and B are not valid.

The best option is to upload file1.avi to a cloud storage service such as Microsoft OneDrive, and then generate a shareable link for the file. You can then paste the link in the Azure Video Indexer website and upload the video from the URL. This way, you can avoid the file size limitation and ensure that the file is accessible and valid2.

You have a Computer Vision resource named contoso1 in West US region.

You must use this resource to resize an image using smart cropping.

Let’s analyze the key points:

Endpoint

Each Azure AI service resource has a regional endpoint.

Since the resource name is contoso1 and is deployed in West US, the correct endpoint will be:

https://contoso1.cognitiveservices.azure.com

The older projectoxford.ai and generic westus.api.cognitive.microsoft.com are legacy endpoints and are not recommended.

Therefore, the correct choice is https://contoso1.cognitiveservices.azure.com .

API Method

The task is to generate a different size of a product photo with smart cropping.

This is done using the Generate Thumbnail API in Computer Vision.

The path for this is:

/vision/v3.1/generateThumbnail

Other options like detect (for object detection) or areaOfInterest (for finding regions of interest) do not generate thumbnails.

Correct Answer:

Endpoint: https://contoso1.cognitiveservices.azure.com

API: /vision/v3.1/generateThumbnail

Computer Vision API reference - Generate Thumbnail

Computer Vision REST API documentation

Azure AI services endpoints

Microsoft References

You have an Azure AI Document Intelligence resource named AIDoc1 in the S0 tier.

You need to identify which files can be uploaded to Document Intelligence Studio for training a custom extraction model.

Supported formats: PDF, TIFF, JPG, PNG, BMP.

Maximum file size: 500 MB per document.

Password-protected documents: Not supported.

S0 tier limits: Same as above (50 pages per document limit also applies).

Now checking the given files:

File1 (JPG, 400 MB, No password) → Supported (under 500 MB, allowed format).

File2 (PDF, 250 MB, No password) → Supported.

File3 (PNG, 180 MB, Password-protected) → Not supported (password locked).

File4 (XLSX, 900 MB) → Not supported (format not supported, exceeds 500 MB).

File5 (PDF, 160 MB, Password-protected) → Not supported (password locked).

Correct Answer: C. File1, File2, and File4 only → Wait, check again: XLSX is not supported, so File4 is invalid. Only File1 and File2 are valid.

Correct Final Answer: A. File1, and File2 only

To build narration for video training content using Custom Neural Voice, we must know where each step is done:

Creating a Custom Neural Voice

A Custom Neural Voice is a text-to-speech (TTS) feature within Azure AI Speech.

It allows you to create a unique, natural-sounding synthetic voice.

The correct tool to build and configure a custom voice is the Speech Studio portal.

Not the Language Understanding portal (LUIS), Azure portal directly, or Bot Framework Composer.

Generating narration

Narration requires converting written text into speech.

This is done via the Text-to-Speech service in Azure AI Speech.

Other options:

Language Understanding → For intent/utterance processing, not narration.

Speaker Recognition → For identifying/authenticating speakers, not narration.

Speech-to-text → Converts spoken words to text (the opposite direction).

Thus:

Custom Neural Voice → Speech Studio portal

Narration → Text-to-speech

Correct Answers:

Custom neural voice: The Speech Studio portal

Narration: Text-to-speech

Custom Neural Voice in Speech Studio

Text-to-Speech overview

Microsoft References

Analysis:

Azure AI Bot Service (A): Helps build chatbots but does not store grounding data → ❌

Azure SQL (B): Possible storage, but not recommended for vector search grounding → ❌

Azure AI Document Intelligence (C): Extracts structured info, not used directly for grounding → ❌

Azure Blob Storage (D): Required for storing raw files used in retrieval-augmented generation (RAG) → ✅

Azure AI Search (E): Used to index, vectorize, and query data for grounding → ✅

Correct Answer:

D. Azure Blob Storage and E. Azure AI Search

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

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.

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.

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.

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.

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 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.

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.

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.

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

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