AI-102 Practice Exam 59 — 20 Questions

Question 1

You are designing an agentic solution using Azure AI Agent Service. The agent needs to be able to both read and write data to an Azure SQL database. Which TWO tools should you configure?

Accepted Answer

Function calling. Function calling is correct because it allows the agent to define custom functions that can execute SQL queries against Azure SQL Database, enabling both read and write operations through a structured API call pattern. Code Interpreter is correct because it can run Python code that uses libraries like pyodbc or SQLAlchemy to connect to Azure SQL Database and perform data manipulation, providing a sandboxed execution environment for dynamic SQL operations.

Answer

KQL

Answer

Grounding with Bing

Answer

Knowledge base

Question 2

A company uses Azure OpenAI to generate marketing copy. They want to ensure that the generated content does not contain offensive language. Which feature should they enable?

Accepted Answer

Enable content filtering at the deployment level.. Azure OpenAI provides built-in content filtering at the deployment level that automatically detects and blocks offensive or harmful language in both input prompts and generated outputs. This feature uses Microsoft's Responsible AI models to enforce safety policies without requiring custom code or manual review, making it the most reliable and scalable solution for preventing offensive content in marketing copy.

Answer

Use DALL-E to generate images instead of text.

Answer

Use a system message instructing the model to avoid offensive language.

Answer

Enable diagnostic logging to review all outputs.

Question 3

Refer to the exhibit. You submit this request to the Azure AI Language service. What is the expected response?

Accepted Answer

Both entity recognition and key phrase extraction results.. The request includes both the `entities` and `keyPhrases` tasks in the `tasks` array, which instructs the Azure AI Language service to perform both entity recognition and key phrase extraction on the same input document. The service processes each specified task independently and returns a combined response with results for both tasks, not just one.

Answer

An error because the request format is invalid.

Answer

Only key phrase extraction results.

Answer

Only entity recognition results.

Question 4

You need to monitor the costs of your Azure AI services across multiple subscriptions. Which Azure tool should you use to track spending and set budgets?

Accepted Answer

Azure Cost Management. Azure Cost Management is the dedicated tool for monitoring, analyzing, and controlling cloud spending across multiple subscriptions. It provides cost analysis, budget creation, and alerting capabilities specifically designed for tracking Azure AI services costs at scale.

Answer

Azure Portal

Answer

Azure Monitor

Answer

Azure Advisor

Question 5

Which TWO Azure AI services can be used to extract text from images as part of an Azure AI Search enrichment pipeline?

Accepted Answer

Azure AI Document Intelligence's read model. Azure AI Document Intelligence's read model is specifically designed to extract printed and handwritten text from images and documents, and it can be integrated as a custom skill in an Azure AI Search enrichment pipeline to populate searchable text fields. Option E is correct because Azure AI Search includes a built-in OCR (optical character recognition) skill that can be added to a skillset to extract text from image files during the indexing process.

Answer

Azure Bot Service

Answer

Azure AI Speech to text

Answer

Azure AI Language translation

Question 6

You are building a knowledge mining solution to extract insights from customer support call transcripts. The solution must identify the customer's issue, the resolution provided, and the sentiment of the call. Which combination of Azure AI services should you use?

Accepted Answer

Azure AI Language (key phrase extraction, entity recognition, sentiment analysis). Azure AI Language provides the specific capabilities needed: key phrase extraction to identify the customer's issue, entity recognition to identify the resolution, and sentiment analysis to determine the call sentiment. These are all built-in features of the Language service, making it the single-service solution for this knowledge mining task.

Answer

Azure AI Translator and Azure AI Search

Answer

Azure AI Speech and Azure AI Search

Answer

Azure AI Document Intelligence and Azure AI Language

Question 7

Which Azure AI service can be used to analyze sentiment in text data?

Accepted Answer

Azure AI Language Service. Azure AI Language Service (formerly Text Analytics) includes a built-in sentiment analysis feature that evaluates text and returns sentiment labels (positive, negative, neutral, mixed) along with confidence scores at the sentence and document level. This makes it the primary service for analyzing sentiment in text data. Azure AI Content Safety is not designed for sentiment analysis; it is intended for harmful content moderation.

Answer

Azure AI Translator

Answer

Azure AI Vision

Answer

Azure AI Content Safety

Answer

Azure AI Speech

Question 8

You are developing a mobile app that allows users to take a photo of a product and get information about it. The app must identify the product from the image. Which Azure AI service should you use?

Accepted Answer

Azure AI Custom Vision with image classification. Azure AI Custom Vision with image classification is specifically designed to identify and categorize products or objects within an image based on trained labels. This service allows you to upload images of products, train a model to recognize them, and then use the model to classify new product photos, making it ideal for a product identification app.

Answer

Azure AI Vision OCR

Answer

Azure AI Face API

Answer

Azure AI Custom Vision with object detection

Question 9

You are using Azure AI Studio to deploy a fine-tuned model for code generation. After deployment, you notice that the model returns nonsensical code snippets. You need to diagnose the issue. What should you check first?

Accepted Answer

Evaluate the model performance on a held-out test dataset.. Evaluating the model on a held-out test dataset is the standard first step to diagnose whether the fine-tuned model has generalized properly or is overfitting. If the model produces nonsensical code, the most likely cause is poor training data quality or overfitting, and a held-out evaluation provides a quantitative measure (e.g., perplexity, BLEU score, or exact match) to confirm this before investigating other factors.

Answer

Verify that the training data is in JSONL format.

Answer

Test the base model without fine-tuning to compare outputs.

Answer

Check the deployment's rate limits and quotas.

Question 10

A company uses Azure Content Moderator to review user-generated images in a social media app. Recently, the team noticed that images containing subtle adult content are not being flagged. What should they do to improve detection without increasing false positives?

Accepted Answer

Configure a human review team using the Review tool to manually inspect flagged content.. Azure Content Moderator is designed to work with human review teams via the Review tool to handle edge cases where automated detection fails. By configuring a human review team, flagged images can be manually inspected to catch subtle adult content that the machine learning model misses, without lowering thresholds that would increase false positives. This approach leverages human judgment to improve detection accuracy while maintaining the existing automated moderation settings.

Answer

Increase the moderation thresholds for adult content.

Answer

Disable the adult classification tier to allow all images to pass through.

Answer

Retrain the Content Moderator model with additional labeled images of adult content.

Question 11

You are a security engineer for a financial services company. The company uses Azure AI Language to analyze customer communications for compliance. The solution processes sensitive personal data. You need to ensure that all data transmitted to the Azure AI Language service is encrypted in transit and that the service endpoint is not accessible from the public internet. Additionally, you must use Microsoft Entra ID for authentication. The current implementation uses API keys and the public endpoint. You need to reconfigure the solution. What should you do?

Accepted Answer

Disable the public network access, configure a private endpoint, enable managed identity, and enforce HTTPS. It addresses all three requirements: disabling public network access removes internet exposure, configuring a private endpoint ensures traffic stays within the Azure backbone and your virtual network, enabling managed identity allows Microsoft Entra ID authentication without API keys, and enforcing HTTPS guarantees encryption in transit via TLS. This combination fully secures the Azure AI Language service for sensitive personal data.

Answer

Configure a private endpoint and continue using the public endpoint for redundancy

Answer

Disable the public network access without configuring a private endpoint

Answer

Enable Microsoft Entra ID authentication but keep the public endpoint and API keys

Question 12

A developer is building an application to extract text from scanned invoices using Azure Computer Vision's Read API. The invoices contain a mix of printed and handwritten text. The developer needs to ensure the highest accuracy for both types. Which parameter should they set in the API call?

Accepted Answer

No special parameter; the Read API automatically handles both.. The Read API in Azure Computer Vision is designed to extract text from images and documents, and it automatically handles both printed and handwritten text without requiring any special parameter. Setting the 'language' parameter to 'en' is optional and only improves accuracy for language-specific text, but it does not enable or disable handwriting recognition. Therefore, no additional parameter is needed to achieve the highest accuracy for both types.

Answer

Set the 'language' parameter to 'en' for English handwriting.

Answer

Specify the 'model-version' as '2022-04-30'

Answer

Use the 'mode' parameter set to 'Handwriting'

Question 13

A developer is configuring an Azure AI Language resource for sentiment analysis. The solution must process social media posts in real-time with a throughput of 1000 requests per minute. After testing, the developer notices that the API returns a 429 (Too Many Requests) error when the load exceeds 500 requests per minute. What is the most likely cause and solution?

Accepted Answer

Upgrade the Azure AI Language resource to a higher tier (e.g., Standard S) to increase the rate limit.. The 429 error indicates the request rate exceeds the resource's allocated tier limit. Azure AI Language resources have predefined rate limits per pricing tier; the Standard S tier offers higher throughput (e.g., 1,000 requests per minute) compared to lower tiers. Upgrading to Standard S directly increases the rate limit to match the required 1,000 requests per minute, making it the correct solution.

Answer

Scale out the resource by creating multiple Azure AI Language instances and load balancing requests.

Answer

Implement retry logic with exponential backoff to handle 429 errors.

Answer

Use Azure API Management to cache responses and reduce calls.

Question 14

A large retail company deploys a custom text classification model using Azure Cognitive Service for Language to categorize customer support tickets into 'Billing', 'Technical', and 'General' categories. The model is trained on 10,000 labeled tickets from the past year. After deployment, the model performs well on new tickets but shows a significant drop in accuracy for tickets submitted during holiday seasons, where the volume of billing issues spikes. The engineering team suspects concept drift. They need to maintain high accuracy without manual retraining every season. Which action should the engineer take?

Accepted Answer

Enable active learning on the model and set up a human review loop for low-confidence predictions.. Active learning in Azure Cognitive Service for Language automatically identifies low-confidence predictions and sends them for human review, creating a continuous feedback loop that adapts to concept drift without manual retraining. This allows the model to improve its accuracy on seasonal billing spikes by learning from newly labeled examples, while the human review loop ensures quality control.

Answer

Add subcategories to the classification schema to better capture seasonal patterns.

Answer

Increase the number of training examples per category to 15,000 each.

Answer

Schedule monthly retraining using the original 10,000 tickets plus the new tickets.

Question 15

Which TWO Azure AI services can be used to implement a content moderation pipeline that detects hate speech and blocks violent images?

Accepted Answer

Azure AI Content Safety. Azure AI Content Safety is correct because it is specifically designed to detect hate speech, profanity, and other harmful text content, while Azure AI Vision Image Analysis can analyze images for violent or inappropriate visual content. Together, they form a comprehensive content moderation pipeline that addresses both text and image moderation requirements.

Answer

Azure AI Translator

Answer

Azure AI Speech to Text

Answer

Azure AI Language sentiment analysis

Question 16

You are building a solution to analyze images of handwritten medical prescriptions. The text is in English and includes drug names and dosages. Which combination of Azure AI services should you use?

Accepted Answer

Azure AI Computer Vision Read API and Azure AI Language. The Azure AI Computer Vision Read API (part of the Image Analysis service) extracts printed and handwritten text from images, including medical prescriptions. Azure AI Language then provides entity recognition to identify drug names and dosages from the extracted text. This combination directly addresses the requirement of analyzing handwritten images and extracting structured medical information.

Answer

Azure AI Custom Vision and Azure AI Language

Answer

Azure AI Document Intelligence and Azure AI Language

Answer

Azure AI Video Indexer and Azure AI Language

Question 17

Your Azure OpenAI application experiences high latency during peak hours. You have already scaled up the deployment to the maximum PTUs. What is the most effective next step to reduce latency?

Accepted Answer

Create multiple deployments across different regions and use Azure Traffic Manager to distribute requests. When PTU deployment is already maxed out, the bottleneck is the capacity of a single regional deployment. Distributing requests across multiple regional deployments via Azure Traffic Manager (using performance or geographic routing) spreads the load, reducing per-deployment contention and lowering latency. This approach leverages regional redundancy and global load balancing without requiring a model change or sacrificing quality.

Answer

Use Azure OpenAI's global deployment with the same PTU

Answer

Switch from GPT-4 to GPT-3.5-turbo

Answer

Increase the token limit per request

Question 18

A company wants to moderate user-generated images for adult content. Which Azure AI Vision feature should they use?

Accepted Answer

Analyze Image API with moderation categories. The Analyze Image API in Azure AI Vision includes built-in moderation categories for detecting adult, racy, and gory content in images. This feature is specifically designed for content moderation without requiring custom training, making it the correct choice for moderating user-generated images for adult content.

Answer

Custom Vision with a custom adult classifier

Answer

Face API

Answer

OCR

Question 19

Refer to the exhibit. You have a skillset with two skills. You run the indexer and find that the output field 'organizations' is empty for documents that clearly contain organization names. The 'keyPhrases' output is populated correctly. What is the most likely cause of the issue?

Accepted Answer

The skill is not configured with a 'defaultLanguageCode' and the documents are not in English.. The 'keyPhrases' output is populated correctly, indicating the text extraction and overall pipeline are functional. The Entity Recognition skill requires a 'defaultLanguageCode' to correctly identify entities; if it is not set and the documents are not in English, the skill may fail to extract organizations, resulting in an empty 'organizations' field. This is a known behavior where the skill defaults to English and cannot process other languages without explicit configuration.

Answer

The skill's 'name' property is set to '#1', which is invalid.

Answer

The 'categories' property is misspelled; it should be 'entityCategories'.

Answer

The input source '/document/content' is incorrect; it should be '/document/text'.

Question 20

You are implementing an agentic solution using Azure AI Agent Service with multiple agents that need to collaborate. Each agent has access to different knowledge bases. You want to ensure that the agents can share context and hand off tasks to each other seamlessly. Which architecture should you use?

Accepted Answer

Use a supervisor agent that delegates to specialized agents, with a shared context store in Azure Cosmos DB. The supervisor agent pattern with a shared context store (e.g., Azure Cosmos DB) enables multiple agents to maintain a consistent conversation state and hand off tasks seamlessly. The supervisor orchestrates specialized agents, each with its own knowledge base, while the shared store ensures context is preserved across agent boundaries, which is essential for collaborative agentic workflows in Azure AI Agent Service.

Answer

Create a single monolithic agent that includes all knowledge bases

Answer

Deploy each agent independently and configure them to call each other via HTTP

Answer

Chain the agents sequentially, passing output from one to the next