Free Microsoft AI-102 Practice Exam with Questions & Answers | Set: 2

To make the chatbot respond only when the answer’s confidence is ≥ 95%, you must set the request body property confidenceScoreThreshold to 0.95 in the Query knowledge bases operation of Custom question answering. The REST API for querying a Custom question answering project is:

POST {Endpoint}/language/:query-knowledgebases?projectName={projectName}&deploymentName={deploymentName}&api-version=2021-10-01

Here, projectName identifies the Custom question answering project you’re querying (the screenshot’s placeholder ), while deploymentName specifies which deployment (for example, production) to use. The request body includes confidenceScoreThreshold (0–1) to filter out answers below that score; setting it to 0.95 enforces the requirement.

Example snippet:

curl -X POST "$LANGUAGE_ENDPOINT/language/:query-knowledgebases?projectName=&deploymentName=production&api-version=2021-10-01" \

-H "Ocp-Apim-Subscription-Key: $LANGUAGE_KEY" \

-H "Content-Type: application/json" \

-d '{

"question": "How much energy does my phone have left?",

"confidenceScoreThreshold": 0.95

}'

References

REST API: Question Answering – Get Answers (shows endpoint with projectName/deploymentName and the confidenceScoreThreshold request property). Microsoft Learn

REST API (newer version) parameter list for projectName/deploymentName. Microsoft Learn

Semantic Kernel supports multiple prompt template languages. Handlebars and Liquid both allow you to bind complex objects (with nested/sub-properties), iterate over collections, and use conditionals—ideal when your prompt needs structured data.

JSONL is a dataset/record format, not a prompt templating language.

YAML is a configuration/serialization format; while SK can store configs in YAML, YAML itself isn’t a prompt templating engine for rendering nested objects in prompts.

“Semantic Kernel” as an option is not a template language; SK provides the runtime and also a simple legacy template syntax, but for complex/nested objects Microsoft recommends Handlebars (cross-language) or Liquid (.NET).

References (Microsoft Docs):

Handlebars prompt templates in Semantic Kernel (supports SK prompts, expressions, iteration, object binding). Microsoft Learn

Liquid prompt templates in Semantic Kernel (example shows passing objects and iterating over nested data). Microsoft Learn

SK prompt template syntax overview (context on SK templating options). Microsoft Learn

==========================

Box 1: Yes

The ActivityHandler.OnMembersAddedAsync method overrides this in a derived class to provide logic for when members other than the bot join the conversation, such as your bot's welcome logic.

Box 2: Yes

membersAdded is a list of all the members added to the conversation, as described by the conversation update activity.

Box 3: No

Azure Storage provides multiple services, each with different data models:

Azure Files

Provides fully managed file shares accessible via SMB/NFS.

Works like a traditional file system (folders and files).

Not key/value.

Azure Blob Storage

Object storage for unstructured data like images, videos, backups, logs.

Identified by container + blob name.

Not strictly a key/value store (though blob name acts as a key).

Azure Table Storage ✅

A NoSQL key/value store for structured, non-relational data.

Data is stored in tables as entities (rows), with properties (columns).

Entities are indexed by PartitionKey + RowKey, forming a unique key/value pair.

Specifically designed for scalable key/value lookups.

Azure Queue Storage

Provides message queueing for communication between components.

Stores ordered messages, not key/value pairs.

Correct Answer: C. Azure Table

Azure Table Storage overview

Azure Storage services comparison

Microsoft References

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

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.

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

Comprehensive Detailed ExplanationThe given code is using the Azure AI Vision client library with the method:

image_analysis = client.analyze_image_in_stream(

image=image_stream,

visual_features=[

VisualFeatureTypes.tags,

VisualFeatureTypes.description

]

)

Breakdown of the functionality:

VisualFeatureTypes.tags → Extracts tags (labels) describing the image (e.g., “dog”, “tree”, “outdoor”), including confidence scores.

VisualFeatureTypes.description → Generates captions (natural-language sentences) that describe the image.

The code explicitly iterates through tags and captions, printing both with their confidence values.

The image is read from the local file system using:

with open(local_image, "rb") as image_stream:

Face recognition is not included because the code does not request VisualFeatureTypes.faces.

Correct Answer Matrix:

Face recognition → No

Tags with confidence → Yes

Read image from local file system → Yes

Azure AI Vision features (tags, description, faces, etc.)

analyze_image_in_stream method

Microsoft References

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

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.