AI-102 Practice Test 15 — 15 Questions

Question 1

Your company deploys an Azure AI Vision solution to detect defects on a manufacturing assembly line. The solution uses a custom object detection model trained on images of products. The model is deployed as a real-time endpoint on an Azure Kubernetes Service (AKS) cluster. Recently, the defect detection accuracy dropped significantly. You suspect data drift because the lighting conditions on the assembly line changed after maintenance. You need to monitor and retrain the model to maintain accuracy. The solution must use Azure AI Foundry's model monitoring capabilities. You also need to automate retraining when drift is detected. What should you do?

Choose an answer to begin — your selection is scored in the full session.

Accepted Answer

Enable model monitoring in Azure AI Foundry, set up drift detection alerts, and create an automated retraining pipeline. Azure AI Foundry's model monitoring provides built-in drift detection capabilities that can automatically monitor input data distributions and trigger alerts when drift is detected. By combining this with an automated retraining pipeline (e.g., using Azure Machine Learning pipelines or Azure DevOps), you can retrain the custom object detection model on new data reflecting the changed lighting conditions without manual intervention, ensuring sustained accuracy.

Answer

Collect more training data from the new lighting conditions and retrain once

Answer

Manually review the model performance weekly and retrain if needed

Answer

Increase the number of replicas in the AKS cluster

Question 2

You need to provide a team of data scientists with access to an Azure Machine Learning workspace. The data scientists should be able to create and run experiments, but they should not be able to delete the workspace or modify its configuration. Which built-in role should you assign?

Accepted Answer

Contributor. The Contributor role allows creating and managing resources within the workspace, including experiments, but not deleting the workspace or modifying its configuration. Option B is wrong because Reader is read-only and cannot create experiments. Option C is wrong because User Access Administrator primarily manages user access and permissions, not resource creation. Option D is wrong because Owner grants full control, including the ability to delete the workspace and modify its configuration.

Answer

Reader

Answer

User Access Administrator

Answer

Owner

Question 3

You are building an agentic solution that needs to process large documents uploaded by users. The agent should extract key information and summarize the content. Which tool should you enable?

Accepted Answer

Code Interpreter. Code Interpreter (now called 'Code Interpreter' in Azure AI Studio/Assistants API) provides a sandboxed Python environment that can execute code to process uploaded files, including parsing large documents, extracting key information, and generating summaries. It handles file I/O, data manipulation, and natural language processing libraries, making it the correct tool for this agentic document-processing task.

Answer

Function calling

Answer

KQL

Answer

Knowledge base

Question 4

An organization uses Microsoft Copilot Studio to build an agent that handles customer inquiries. The agent uses a custom topic with a Power Automate flow to check order status. The flow returns a JSON object with order details. The agent needs to display the order status and estimated delivery date in a formatted message. How should the agent parse the JSON response?

Accepted Answer

Use the ParseJSON Power Fx function to convert the JSON string to a record.. Copilot Studio uses Power Fx, a low-code language, and the `ParseJSON` function is the native way to convert a JSON string into a record that can be used in agent variables and message formatting. This allows the agent to directly access properties like `orderStatus` and `estimatedDeliveryDate` from the JSON object returned by the Power Automate flow without requiring custom code or modifying the flow's output structure.

Answer

Write a custom code action in C# to parse the JSON.

Answer

Use the built-in JSON parser in Copilot Studio.

Answer

Modify the Power Automate flow to return individual variables instead of JSON.

Question 5

Refer to the exhibit. You have this skillset definition for an Azure AI Search enrichment pipeline. You notice that the entity recognition skill is not executing on any document. What is the most likely cause?

Accepted Answer

The input source path in the entity recognition skill should be relative to the context, not absolute. The entity recognition skill has its context set to '/document/pages/*', which means it iterates over each page in the split output. However, its input source is '/document/pages/*' (absolute path), which points to the entire page array element rather than the text content within each page. The input source should be relative to the context, e.g., 'text' if the page had a property, or simply the context itself if the page is a string. Using an absolute path that matches the context can cause the skill to fail because it expects a scalar input, but the context iteration provides the array element. Therefore, the correct fix is to make the input source relative, such as using 'text' or '/document/pages/*/text' appropriately. Option D correctly identifies this issue.

Answer

The entity recognition skill requires a language code that is missing

Answer

The split skill is not producing pages because the content is too short

Answer

The entity recognition skill is not registered in the skillset

Question 6

A company is designing a solution that uses Azure Cognitive Services for text analytics. The solution must meet the following requirements: 
- Detect sentiment in customer feedback. 
- Extract key phrases from the feedback. 
- Identify the language of the feedback automatically. 
- Ensure that the solution can scale to handle thousands of requests per second. 
Which TWO actions should the company take?

Accepted Answer

Use the Text Analytics API for sentiment analysis and key phrase extraction.. The Text Analytics API (part of Azure Cognitive Services for Language) provides built-in capabilities for sentiment analysis, key phrase extraction, and language detection within a single API call. This eliminates the need for separate services and directly satisfies the requirements for detecting sentiment, extracting key phrases, and identifying language automatically.

Answer

Deploy a separate Language Detection service for language identification.

Answer

Use the Free pricing tier to reduce costs.

Answer

Use Azure Functions to aggregate results from multiple API calls.

Question 7

You are using Azure AI Custom Vision to classify images of animals. The training set has 1000 images of cats and 1000 images of dogs. After training, the model performs well on the test set. However, when deployed, it misclassifies images of wolves as dogs. What is the most likely cause?

Accepted Answer

The training set does not include enough negative examples that look like dogs but are not.. The model misclassifies wolves as dogs because the training set lacks negative examples that are visually similar to dogs but belong to a different class. Custom Vision learns to distinguish classes based on the features present in the training images; without images of wolf-like canines labeled as 'not dog,' the model has no basis to reject wolves. This is a classic case of insufficient hard negative mining, where the model generalizes too broadly for the 'dog' class.

Answer

The probability threshold is set too low.

Answer

The model is overfitted to the training data.

Answer

The training set has class imbalance.

Question 8

Which TWO configurations are required to enable incremental enrichment in Azure AI Search?

Accepted Answer

Define a projection in the skillset to store enriched data.. Defining a projection in the skillset is required to store enriched data in a knowledge store, which is a prerequisite for incremental enrichment. Incremental enrichment relies on caching enriched content so that only changed documents are reprocessed, and projections define how that enriched data is stored in Azure Storage for later reuse.

Answer

Configure the indexer to run in 'once' mode.

Answer

Enable blob metadata extraction in the indexer.

Answer

Add a custom skill that outputs a hash of the document content.

Question 9

You need to generate an image of a cat wearing a hat using Azure OpenAI. Which model should you use?

Accepted Answer

DALL-E. DALL-E is the correct model because it is specifically designed by OpenAI for generating images from text descriptions. Azure OpenAI Service hosts DALL-E, enabling you to create images like 'a cat wearing a hat' by providing a natural language prompt. Other models like Whisper, GPT-4, and Codex are optimized for speech recognition, text generation, and code generation respectively, not image synthesis.

Answer

Whisper

Answer

GPT-4

Answer

Codex

Question 10

A company is developing a generative AI solution that must process sensitive customer data. They need to ensure that data remains within their Azure tenant and is not used to improve the base model. Which configuration is required in Azure OpenAI?

Accepted Answer

Opt out of abuse monitoring and data logging in the Azure OpenAI Studio.. Opting out of abuse monitoring and data logging in Azure OpenAI Studio ensures that sensitive customer data is not sent to Microsoft for review or used to improve the base model. This configuration is specifically designed for customers who need to process sensitive data while maintaining data residency within their Azure tenant, as it disables the default logging and human review processes that could expose data outside the tenant.

Answer

Enable customer-managed keys for encryption.

Answer

Use a private endpoint to restrict access to the service.

Answer

Configure data residency to keep data in a specific region.

Question 11

You are designing a knowledge mining solution for a publishing company that needs to extract metadata from thousands of book manuscripts in various formats (PDF, Word, EPUB). The solution must identify authors, publication dates, and chapter titles. You are using Microsoft Foundry with Azure AI Search and Azure AI Document Intelligence. The manuscripts are stored in Azure Blob Storage. You need to ensure that the solution can handle all file formats. You have configured a skillset with a Document Intelligence skill for the PDFs and Word documents. However, the EPUB files are not being processed. What should you do to include EPUB files in the enrichment pipeline?

Accepted Answer

Develop a custom skill that converts EPUB files to plain text and add it to the skillset.. Azure AI Search indexer does not natively support EPUB files. The Document Intelligence skill can only process formats it supports (PDF, Word, etc.). Therefore, a custom skill is needed to convert EPUB files to plain text or a supported format before they can be processed by the enrichment pipeline. Option A is wrong because Azure AI Document Intelligence does not support EPUB directly. Option C is wrong because the Document Intelligence skill cannot be modified to accept new formats. Option D is wrong because registering a new data source type does not enable processing of unsupported file formats.

Answer

Use Azure AI Document Intelligence to extract text from EPUB files directly.

Answer

Modify the Document Intelligence skill to accept EPUB files.

Answer

Register a new data source type for EPUB in Azure AI Search.

Question 12

You are planning a solution that uses Azure AI Language to analyze customer feedback from social media posts. The solution must: - Detect sentiment (positive, negative, neutral) for each post. - Extract key phrases. - Support English and Spanish languages. - Run asynchronously for a batch of 10,000 posts. - Use the least expensive option that meets requirements. What should you do?

Accepted Answer

Use the Azure AI Language service with the built-in sentiment analysis and key phrase extraction capabilities. Process posts in batches using the async API.. Azure AI Language's built-in sentiment analysis and key phrase extraction natively support both English and Spanish, and the async batch API is designed for high-volume processing (e.g., 10,000 posts) at a lower cost than per-document calls. This approach meets all requirements without custom models or translation overhead.

Answer

Build a custom text classification model in Azure AI Language to detect sentiment and extract key phrases.

Answer

Use the Azure AI Language service with the single-document API for each post.

Answer

Use Azure AI Translator to translate all posts to English, then use Azure AI Language for analysis.

Question 13

You are planning an Azure AI solution that processes sensitive customer data. Compliance requires encryption at rest using a customer-managed key (CMK) stored in Azure Key Vault. The AI resource must also be accessible only from specific virtual networks. Which two configurations are necessary? (Choose two.)

Accepted Answer

Enable customer-managed key encryption for the Azure AI service.. This is a multi-select question requiring two correct answers. Option C is correct because enabling customer-managed key encryption for the Azure AI service meets the compliance requirement for encryption at rest with CMK stored in Azure Key Vault. Option E is correct because configuring private endpoints ensures the AI resource is accessible only from specific virtual networks, providing network isolation. Option A is incorrect because a system-assigned managed identity is not required for CMK or network access; it is used for authentication. Option B is incorrect because Azure Firewall inspects outbound traffic, which is not mandated by the requirements. Option D is incorrect because public network access must be disabled when using private endpoints; allowing selected IP addresses does not achieve the required virtual network restriction.

Answer

Assign a system-assigned managed identity to the Azure AI service.

Answer

Deploy Azure Firewall to inspect outbound traffic.

Answer

Enable public network access from selected IP addresses.

Question 14

A security company uses Azure Video Analyzer on IoT Edge to detect intrusions. The edge device has limited compute and network. They need to reduce latency. What should they configure?

Accepted Answer

Set a high minimum confidence threshold for detection.. Setting a high minimum confidence threshold for detection reduces the number of false positives and the volume of events that need to be processed and transmitted. This directly lowers the computational load on the edge device and reduces network bandwidth usage, thereby decreasing latency for actionable intrusion alerts.

Answer

Increase the video resolution sent to the cloud.

Answer

Enable cloud-based processing for all frames.

Answer

Use multiple AI models simultaneously.

Question 15

Which THREE factors should you consider when choosing between a pre-built model and a custom model in Azure AI Language?

Accepted Answer

Domain-specific vocabulary coverage. Pre-built models in Azure AI Language are trained on general web-scale data and may lack domain-specific vocabulary (e.g., medical terminology, legal jargon). If your use case requires understanding specialized terms, a custom model trained on domain-specific labeled data will achieve higher accuracy. The choice hinges on whether the pre-built model's general vocabulary covers your domain's unique terms.

Answer

Need for a trained endpoint

Answer

Model size and memory footprint