AI-102 Practice Test 35 — 15 Questions

Question 1

You are designing a knowledge mining solution that ingests documents from SharePoint Online and makes them searchable using Azure AI Search. The solution must extract text from images and perform optical character recognition (OCR) on embedded images within PDFs. Which built-in skill should you include in the skillset?

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

Accepted Answer

OCR skill. The OCR skill (Optical Character Recognition) is the correct built-in skill for extracting text from images and performing OCR on embedded images within PDFs in Azure AI Search. It specifically handles image files (e.g., JPEG, PNG) and embedded images in PDFs, outputting text that can be indexed and searched. Other skills like translation, key phrase extraction, or entity recognition do not perform text extraction from images.

Answer

Translation skill

Answer

Key phrase extraction skill

Answer

Entity recognition skill

Question 2

You run the Azure CLI command 'az search indexer list --search-service mysearch --query "[].{name:name, status:status, lastResult:lastResult}"' and get the above output. Your indexer shows 5 warnings. What should you do to investigate the warnings?

Accepted Answer

Run 'az search indexer show --name myindexer' and review the 'warnings' array in the output.. The 'az search indexer list' command with the query you used returns a summary of indexer status and last result, but it does not include the detailed 'warnings' array. To investigate the 5 warnings, you need to use 'az search indexer show --name myindexer', which returns the full indexer execution history, including a 'warnings' array that lists each warning with its message and details. This allows you to understand the nature of each warning and take corrective action if needed.

Answer

Run 'az search indexer run --name myindexer' to trigger a new run.

Answer

Ignore the warnings because they are not errors.

Answer

Run 'az search indexer reset --name myindexer' to reset the indexer.

Question 3

A financial services company uses Azure AI Language's custom text classification to categorize loan applications as 'Approved', 'Denied', or 'Review Required'. The model is trained on historical data but is producing poor accuracy on new applications. The data scientist suspects data leakage between training and test sets. What should the data scientist do to validate this?

Accepted Answer

Split the data chronologically and ensure no overlapping data between train and test sets.. Data leakage occurs when information from outside the training set inadvertently influences the model, often due to overlapping or non-independent data splits. By splitting the data chronologically (e.g., training on older applications and testing on newer ones), the data scientist ensures that no future information leaks into the training process, which directly validates whether temporal leakage is causing poor accuracy. This approach is standard for time-series or sequential data like loan applications, where patterns may shift over time.

Answer

Increase the training dataset size and retrain the model.

Answer

Use k-fold cross-validation during training.

Answer

Adjust the classification confidence threshold.

Question 4

Refer to the exhibit.

{
  "content_filters": [
    {
      "type": "hate",
      "action": "block",
      "severity": "high"
    },
    {
      "type": "sexual",
      "action": "block",
      "severity": "medium"
    },
    {
      "type": "self_harm",
      "action": "block",
      "severity": "low"
    }
  ]
}

You deploy an Azure OpenAI model with the above content filter configuration. A user submits a prompt that the system rates as "hate" at severity level "medium". What happens?

Accepted Answer

The prompt is allowed because the severity is below the threshold.. The content filter configuration blocks 'hate' content only at severity level 'high'. Since the user's prompt was rated as 'hate' at severity 'medium', it falls below the configured threshold and is allowed. Azure OpenAI content filters evaluate severity levels (low, medium, high) and apply the configured action only when the detected severity meets or exceeds the specified threshold.

Answer

The prompt is blocked because hate content is detected.

Answer

The prompt is blocked because the severity is medium.

Answer

The prompt is allowed because the hate filter is not configured for medium.

Question 5

A company plans to deploy an Azure AI solution that processes sensitive customer data. The solution must comply with GDPR and ensure data residency within the European Union. Which Azure resource configuration should be used?

Accepted Answer

Create an Azure AI services resource in a specific EU region and set the data residency option to 'EU'.. Azure AI services allow you to specify a data residency option when creating the resource in a specific EU region, ensuring that all customer data remains within the European Union as required by GDPR. This configuration explicitly restricts data processing and storage to the chosen geographic boundary, meeting compliance and residency mandates.

Answer

Deploy the Azure AI services in multiple regions globally and use geo-replication.

Answer

Use the Azure AI services 'Data Residency' SKU.

Answer

Use the Free tier of Azure AI services.

Question 6

You are deploying a custom image classification model using Azure AI Custom Vision. The model must achieve high accuracy on a dataset with subtle differences between classes. However, the training set is small (200 images per class). Which strategy should you use to improve model performance?

Accepted Answer

Use transfer learning with a pre-trained model and fine-tune. Transfer learning with a pre-trained model (e.g., ResNet, EfficientNet) is ideal for small datasets because it leverages features learned from large-scale datasets like ImageNet. Fine-tuning adjusts only the final layers to the new task, preventing overfitting and achieving high accuracy even with subtle inter-class differences. Custom Vision automatically uses transfer learning, making option D the correct strategy.

Answer

Enable hyperparameter tuning and increase the number of iterations

Answer

Apply aggressive data augmentation and train from scratch

Answer

Use a larger batch size and train for more epochs

Question 7

You are responsible for managing costs for multiple Azure AI services in your organization. You notice that provisioned throughput units (PTUs) for Azure OpenAI are not fully utilized. What is the most cost-effective action to optimize spending?

Accepted Answer

Reduce the number of provisioned PTUs or switch to pay-as-you-go. Provisioned throughput units (PTUs) represent a fixed capacity commitment. If PTUs are underutilized, the most cost-effective action is to reduce the number of PTUs or switch to the pay-as-you-go (PAYG) model, which charges only for tokens consumed. This directly aligns with cost optimization by eliminating the fixed cost of unused capacity.

Answer

Configure auto-scaling to reduce PTUs during low usage

Answer

Move the resource to a different region with lower pricing

Answer

Stop the Azure OpenAI service when not in use

Question 8

You are deploying a custom Azure AI Language question answering project. The solution must only answer questions based on a specific set of internal FAQ documents. Which data source type should you use when creating the project?

Accepted Answer

URLs or files containing FAQ content. Azure AI Language custom question answering is designed to ingest structured FAQ content from URLs or files. When you create a custom project, selecting 'URLs or files containing FAQ content' as the data source type allows the service to automatically extract question-answer pairs from the provided documents, ensuring the solution only answers questions based on that specific set of internal FAQs.

Answer

Prebuilt model from Azure AI Language

Answer

Azure SQL Database with a QnA Maker schema

Answer

Azure Cognitive Search index

Question 9

A hospital uses Azure Cognitive Service for Language to extract medical entities from clinical notes. The extraction accuracy for medication names and dosages is low. The engineer needs to improve performance without adding new training data. Which solution should the engineer implement?

Accepted Answer

Use custom entity recognition with a prebuilt healthcare entity component.. The engineer can use custom entity recognition with a prebuilt healthcare entity component, which leverages the existing Text Analytics for Health model's pre-trained entities (including medication names and dosages) without requiring additional training data. This approach combines the prebuilt healthcare model's high accuracy for medical entities with custom entity recognition to fine-tune extraction for specific clinical notes, improving performance without adding new annotated data.

Answer

Add more training data with annotated entities.

Answer

Retrain the Text Analytics for Health model with additional labeled data.

Answer

Increase the confidence threshold for entity extraction.

Question 10

Your team is building a mobile app that uses Azure Custom Vision to classify plant species. The app must work offline and sync labeled images when connectivity is restored. Which SDK feature should you use?

Accepted Answer

Export the model as a TensorFlow or CoreML model for on-device inference. Azure Custom Vision allows exporting trained models to formats like TensorFlow, CoreML, ONNX, or Docker for on-device inference. This enables the mobile app to run classification locally without network connectivity, and the Custom Vision SDK includes a method to upload labeled images for offline training sync when connectivity is restored.

Answer

Azure IoT Edge runtime on the phone

Answer

Azure API Management with caching

Answer

Continuous deployment integration

Question 11

You are building a chatbot using Azure OpenAI Service. The chatbot must not disclose sensitive information such as passwords or credit card numbers. Which Azure AI service should you integrate to filter such content?

Accepted Answer

Azure AI Content Safety. Azure AI Content Safety is the correct service because it provides pre-built content filters that can detect and block sensitive information such as passwords, credit card numbers, and other personally identifiable information (PII) in text and images. It integrates directly with Azure OpenAI Service to apply these filters to both input prompts and output completions, ensuring that sensitive data is not disclosed in chatbot responses.

Answer

Azure AI Language

Answer

Azure AI Bot Service

Answer

Azure AI Search

Question 12

You are an AI engineer at a healthcare company. The company uses Azure Cognitive Services to process medical records. They have a Computer Vision resource deployed in the East US region. Recently, they implemented a custom vision model for detecting specific anomalies in X-ray images. The model was trained using the Custom Vision portal and exported as a TensorFlow model. They deployed the model to an Azure Kubernetes Service (AKS) cluster using a Docker container. The container runs the model and exposes a REST API endpoint for inference. The endpoint is used by a web application that is also hosted in the same AKS cluster. The web application is experiencing high latency when making inference requests. The latency spikes up to 10 seconds during peak hours. The AKS cluster has autoscaling enabled based on CPU metrics. The container's resource limits are set to 1 CPU core and 2 GB memory. The model's inference time on a single image is approximately 500 ms on the development machine. The team has not changed the model or the application code recently. The number of concurrent users has increased by 50% in the last month. What should you do to reduce inference latency?

Accepted Answer

Increase the CPU limit for the container to 4 cores.. The inference latency is caused by CPU saturation during peak hours. The container is limited to 1 CPU core, and with a 50% increase in concurrent users, the single core becomes a bottleneck, causing inference times to spike. Increasing the CPU limit to 4 cores allows the model to process multiple requests in parallel, reducing queue wait times and overall latency.

Answer

Increase the memory limit for the container to 8 GB.

Answer

Deploy additional replicas of the container and use a load balancer.

Answer

Optimize the model by quantizing it to reduce inference time.

Question 13

Your company uses Azure AI Language to analyze customer feedback. You need to extract key phrases from reviews in multiple languages. Which feature should you use?

Accepted Answer

Key phrase extraction. Key phrase extraction is the correct feature because it is specifically designed to identify and extract the most important points or topics from text, regardless of the language. Azure AI Language's key phrase extraction supports multiple languages and returns a list of key phrases that represent the main subjects discussed in the customer feedback, which directly meets the requirement.

Answer

Named entity recognition

Answer

Language detection

Answer

Sentiment analysis

Question 14

Your company uses Azure OpenAI Service to generate product descriptions. You need to ensure that the generated content does not include offensive language and adheres to responsible AI principles. What should you implement?

Accepted Answer

Configure content filters in Azure OpenAI. Content filters in Azure OpenAI allow you to define categories (e.g., hate, violence, self-harm) and severity levels (low, medium, high) to automatically block or flag offensive language in generated outputs. This directly enforces responsible AI principles by preventing harmful content from being surfaced to users, without requiring model retraining or encryption changes.

Answer

Enable customer-managed key encryption

Answer

Fine-tune the model with a curated dataset

Answer

Set usage limits and throttling

Question 15

An image was submitted to Azure Content Moderator's Image Moderation API. The application uses a threshold of 0.5 for Category1 (adult) to trigger a review. Based on the exhibit, what should the application do with this image?

Accepted Answer

Escalate the image to a human reviewer because Category1 score exceeds the threshold.. The application's threshold for Category1 (adult) is 0.5, and the exhibit shows a Category1 score of 0.6, which exceeds this threshold. Even though ReviewRecommended is false, the application's custom threshold overrides the default recommendation, requiring escalation to a human reviewer for manual judgment. This aligns with Azure Content Moderator's design where you can set your own thresholds to trigger reviews regardless of the API's built-in recommendation.

Answer

Auto-approve the image because ReviewRecommended is false.

Answer

Auto-reject the image because no offensive terms were found.

Answer

Log the inconsistency and continue processing without action.