AI-102 Practice Test 38 — 15 Questions

Question 1

You are designing a solution to extract structured data from a large number of handwritten forms. The forms are scanned and stored as images. Which Azure AI feature should you use?

Accepted Answer

Azure AI Document Intelligence's OCR capability. Azure AI Document Intelligence's OCR capability is specifically designed to extract structured data from scanned documents, including handwritten forms. It uses advanced optical character recognition (OCR) and layout analysis to identify text, tables, and key-value pairs, making it the correct choice for this scenario.

Answer

Azure AI Vision's image analysis

Answer

Azure AI Speech to text

Answer

Azure Bot Service

Question 2

You are developing a bot using Microsoft Bot Framework and Azure AI Language. The bot must handle user intents that change mid-conversation. Which feature should you implement?

Accepted Answer

Adaptive dialogs. Adaptive dialogs are designed for dynamic, event-driven conversations where user intents can change mid-conversation. They use a trigger-based model (e.g., onIntent, onTurn) that allows the bot to react to new intents at any point, unlike linear dialog models. This makes them ideal for handling mid-conversation intent shifts without requiring predefined dialog flows.

Answer

Prompt dialogs

Answer

Waterfall dialogs

Answer

QnA Maker knowledge base

Question 3

You are planning to use Azure AI Content Safety to moderate user-generated content in a social media application. The solution must detect hate speech and self-harm content. Which Content Safety features should you enable?

Accepted Answer

Hate and self-harm content filters. Azure AI Content Safety provides pre-built filters for specific harm categories, including hate speech and self-harm. Enabling the 'Hate and self-harm content filters' directly activates the detection models for these categories, meeting the requirement without needing custom categories or additional features.

Answer

Severity levels for all categories

Answer

Custom categories for hate speech and self-harm

Answer

Image moderation

Question 4

You are developing an Azure AI Language solution to analyze customer support tickets. Each ticket has a subject and a description. You need to automatically classify tickets into categories (e.g., 'billing', 'technical', 'account') and extract the product name mentioned. You have a labeled dataset of 10,000 tickets with category labels and product name annotations. The solution must be cost-effective and easy to retrain as new categories emerge. You want to use a single Azure AI Language resource. Which approach should you use?

Accepted Answer

Use custom text classification for category and custom named entity recognition for product name extraction.. Custom text classification can be trained on the labeled dataset to categorize tickets, and custom named entity recognition (NER) can be trained to extract product names from the text. Both services are part of the Azure AI Language resource, allowing a single resource to handle both tasks. This approach is cost-effective and easy to retrain as new categories emerge. Option A is incorrect because key phrase extraction is a prebuilt feature that returns general key phrases, not specifically trained to extract product names, and may miss them or include irrelevant phrases. Option B is incorrect because conversational language understanding (CLU) is optimized for multi-turn conversational flows and requires more complex configuration, making it less suitable for single-turn ticket classification and less cost-effective. Option D is incorrect because prebuilt NER only recognizes common entity types (e.g., person, organization) and cannot extract custom product names unless they match those predefined types.

Answer

Use custom text classification for category and key phrase extraction for product name.

Answer

Use conversational language understanding (CLU) to handle both classification and entity extraction in a single model.

Answer

Use custom text classification for category and prebuilt named entity recognition for product name extraction.

Question 5

Your knowledge mining pipeline uses Azure AI Search to index PDF files. You need to extract text from the PDFs and also recognize embedded tables. Which built-in skill should you use?

Accepted Answer

Document Extraction skill. The Document Extraction skill is designed to extract text from binary files such as PDFs. However, it does not natively extract embedded tables as structured data. For table recognition, you would typically need additional processing, such as using the OCR skill for image-based tables or integrating Azure Document Intelligence. Therefore, among the provided options, Document Extraction is the most relevant for text extraction but does not fully address table recognition without supplementary steps.

Answer

OCR skill

Answer

Custom Web API skill

Answer

Entity Recognition skill

Question 6

You notice a spike in errors (HTTP 429) on a specific day. What is the most likely cause?

Accepted Answer

The number of calls exceeded the rate limit for the service tier.. HTTP 429 (Too Many Requests) is a rate-limiting response that occurs when the number of API calls exceeds the allowed threshold for the service tier. In Azure AI services, each pricing tier has a specific requests-per-second (RPS) or requests-per-minute (RPM) limit, and exceeding this limit triggers a 429 error to protect backend resources.

Answer

Network connectivity issues.

Answer

Authentication tokens expired.

Answer

Invalid API keys were used.

Question 7

Refer to the exhibit. You are reviewing a Bicep template for deploying an Azure AI Language resource. After deployment, you need to ensure that the resource uses a private endpoint to block public access. Which additional resource should you include in the template?

Accepted Answer

A Private Endpoint resource linked to the Cognitive Services account. A Private Endpoint resource, when linked to the Cognitive Services account via the `privateLinkServiceId` property, assigns a private IP address from a virtual network to the Azure AI Language resource. This blocks all public access by default when the resource's `publicNetworkAccess` property is set to 'Disabled', ensuring traffic only flows over the Microsoft backbone network through Azure Private Link.

Answer

A service endpoint for Microsoft.CognitiveServices

Answer

A virtual network peering connection

Answer

A virtual network gateway

Question 8

A company uses this skillset in an Azure AI Search enrichment pipeline. They notice that the enrichment pipeline fails when processing a document larger than 5000 characters. What is the most likely cause?

Accepted Answer

The output field mapping is missing or incorrect. The enrichment pipeline fails because the output field mapping is missing or incorrect. When a skillset processes documents, the output of each skill must be explicitly mapped to an index field; if this mapping is absent or misconfigured, the pipeline cannot store the enriched data and fails, especially for larger documents that produce more output data.

Answer

The maximum page length is too small

Answer

The default language code is not supported

Answer

The text split mode should be 'sentences'

Question 9

Which THREE are valid uses of Azure AI Vision Image Analysis 4.0? (Select three.)

Accepted Answer

Extract printed text from an image using OCR. Azure AI Vision Image Analysis 4.0 includes an OCR (Optical Character Recognition) capability that extracts printed and handwritten text from images. This is a core feature of the service, exposed via the `ocr` API or the `read` operation in the Image Analysis 4.0 SDK.

Answer

Transcribe spoken audio from a video file

Answer

Translate text found in an image to another language

Question 10

Which TWO actions are required to enable private endpoint connectivity for an Azure AI Language resource?

Accepted Answer

Disable public network access on the AI resource. To enable private endpoint connectivity for an Azure AI Language resource, you must disable public network access on the AI resource (Option A) to ensure all traffic goes through the private endpoint. You also need to create the private endpoint in a subnet of a virtual network (Option B) to establish the private connection. Option C is not required because Azure Firewall rules are not needed for private endpoints; network policies are handled by NSG and UDR. Option D is incorrect because a private DNS zone is optional but not required—it is recommended for name resolution but not a requirement. Option E is wrong because service tags are not required for private endpoints; they are used for public network access rules.

Answer

Configure an Azure Firewall rule to allow the private endpoint

Answer

Create a private DNS zone for the resource

Answer

Add a service tag to the network security group

Question 11

You have an Azure AI Search indexer that is configured to index PDF files from Azure Blob Storage. The indexer is not extracting any text from the PDFs, and no errors are reported. You review the indexer definition as shown. What is the most likely cause?

Accepted Answer

The parsingMode is set to 'json' instead of 'default' or 'text'. The parsingMode set to 'json' tells the indexer to expect JSON files, not PDFs. Since PDFs are binary or text-based, the indexer cannot extract any content, but because it does not fail (JSON parsing simply returns no text), no error is reported. Changing parsingMode to 'default' or 'text' allows the indexer to correctly parse the PDF binary stream and extract text.

Answer

The field mapping from 'content' to 'content' is redundant and causes a conflict

Answer

The field mapping for 'metadata_storage_path' should be to 'metadata_storage_path'

Answer

The dataToExtract is set to 'contentAndMetadata' which is not supported for PDFs

Question 12

You are developing a generative AI application that must comply with responsible AI principles. Which Azure AI service should you use to detect and filter harmful content in both input prompts and output responses?

Accepted Answer

Azure AI Content Safety. Azure AI Content Safety is the dedicated Azure service for detecting and filtering harmful content such as hate speech, violence, self-harm, and sexual content in both user prompts and AI-generated responses. It provides configurable severity levels and integrates directly with generative AI workflows to enforce responsible AI policies, making it the correct choice for this requirement.

Answer

Microsoft Purview

Answer

Azure OpenAI Service

Answer

Azure AI Language

Question 13

You are deploying an Azure AI Language service custom text classification model. After training, the model achieves 95% accuracy on the test set but only 60% on a held-out validation set. What is the most likely cause?

Accepted Answer

Overfitting to the training data. A 95% accuracy on the test set but only 60% on a held-out validation set is a classic sign of overfitting. The model has memorized patterns specific to the training and test sets (which may share distribution or preprocessing artifacts) but fails to generalize to unseen data. In Azure AI Language custom text classification, overfitting often occurs when the model is too complex relative to the amount of training data or when hyperparameters like learning rate or number of epochs are not tuned properly.

Answer

Data leakage between training and test sets

Answer

Insufficient training data

Answer

Label imbalance in the training data

Question 14

You are building a custom text classification solution in Azure AI Language. You have a dataset with 10 categories and 1000 labeled documents. You need to choose the best project type. What should you use?

Accepted Answer

Custom text classification (single or multi-label). Custom text classification (single or multi-label) is the correct project type because you have a labeled dataset with 10 categories and need to train a model to classify text into those specific categories. Azure AI Language provides a custom text classification feature that allows you to train a model using your own labeled data, supporting both single-label and multi-label classification scenarios. This is the only option that enables you to build a bespoke classifier tailored to your 10-category dataset.

Answer

Conversational Language Understanding (CLU)

Answer

Key Phrase Extraction

Answer

Prebuilt Text Classification API

Question 15

You run the PowerShell script shown to audit your Azure AI Agent Service agents. The script outputs that several agents have no tools configured. What is the impact on those agents?

Accepted Answer

The agents can only respond to queries using the model's built-in knowledge, without ability to perform actions. Azure AI Agent Service agents without tools configured rely solely on the model's built-in knowledge (e.g., GPT-4o's training data) to generate responses. They cannot execute external actions like calling APIs, querying databases, or running code, which are enabled only when tools (e.g., code interpreter, function calling, or Azure Functions) are explicitly attached. This is by design: tools extend the agent's capabilities beyond the model's static knowledge.

Answer

The agents cannot be deployed until tools are added

Answer

The agents cannot start conversations with users

Answer

The agents will use default tools provided by Azure