AI-102 Practice Test 31 — 15 Questions

Question 1

A logistics company receives shipping manifests as PDF documents. They need to extract the shipper name, consignee, and total weight from each document. The documents have a consistent layout. Which Azure AI service should they use?

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

Accepted Answer

Azure AI Document Intelligence with a custom extraction model.. Document Intelligence is built to extract fields from documents, especially forms with consistent layouts. A custom extraction model can be trained to identify shipper name, consignee, and total weight accurately. The other services either do not handle document layout or are not designed for field extraction from PDFs.

Answer

Azure AI Translator to convert the PDF to text and then parse with regex.

Answer

Azure AI Language with custom named entity recognition (NER).

Answer

Azure AI Vision with OCR and then custom text classification.

Question 2

You are using Azure AI Language to analyze customer feedback. You need to identify the sentiment of each sentence within a review, not just the overall document sentiment. Which feature should you use?

Accepted Answer

Sentiment analysis with opinion mining enabled.. Sentiment analysis in Azure AI Language can return sentiment at the document and sentence level when opinion mining is enabled. This provides the granularity needed to see sentiment per sentence. Key phrase extraction, custom classification, and entity linking do not offer built-in sentence-level sentiment.

Answer

Key phrase extraction.

Answer

Custom text classification with sentiment labels.

Answer

Entity linking.

Question 3

You are building an application that must detect and redact personally identifiable information (PII) from free-text support tickets before storing them. The tickets are written in English, and you need to identify entities such as names, phone numbers, and email addresses, and replace them with asterisks. You plan to use the Azure AI Language service. Which API endpoint should you call?

Accepted Answer

POST /language/:analyze-text with kind set to "PiiEntityRecognition" in the request body.. The PiiEntityRecognition kind in the analyze-text endpoint is purpose-built for identifying and redacting personal data. It returns both the detected entities and a redactedText field where entities are masked with asterisks. The other kinds either detect different entity types or serve different NLP tasks, and none provide the required redaction behavior.

Answer

POST /language/:analyze-text with kind set to "KeyPhraseExtraction" in the request body.

Answer

POST /language/:analyze-text with kind set to "EntityRecognition" in the request body.

Answer

POST /language/:analyze-conversations with kind set to "ConversationPII" in the request body.

Question 4

You are developing a conversational language understanding (CLU) project in Azure AI Language. The project must recognize user intents and extract entities from utterances. You have trained and deployed the model. You need to call the prediction API from a client application. The deployment name is 'prod' and the project name is 'HRBot'. Which URL should you use to send an utterance for prediction?

Accepted Answer

https://<resource-name>.cognitiveservices.azure.com/language/analyze-conversations/projects/HRBot/deployments/prod/:analyze-conversations?api-version=2023-04-01. The CLU prediction endpoint requires the project name and deployment name as path segments under the analyze-conversations operation, along with a supported API version. The correct URL includes /language/analyze-conversations/projects/{project}/deployments/{deployment}/:analyze-conversations?api-version=2023-04-01. Query-string routing, the wrong operation name, or an outdated API version will not work for CLU predictions.

Answer

https://<resource-name>.cognitiveservices.azure.com/language/:analyze-conversations?projectName=HRBot&deploymentName=prod&api-version=2023-04-01

Answer

https://<resource-name>.cognitiveservices.azure.com/language/analyze-text/projects/HRBot/deployments/prod?api-version=2023-04-01

Answer

https://<resource-name>.cognitiveservices.azure.com/language/analyze-conversations/projects/HRBot/deployments/prod?api-version=2022-05-01

Question 5

You are using Azure AI Language's question answering feature to build a bot that answers employee questions from a set of HR policy documents. You need to ensure the bot provides accurate answers and can handle follow-up questions. Which two actions should you take? (Choose two.)

Accepted Answer

Enable multi-turn extraction to create follow-up prompts for related questions.. To improve accuracy and handle follow-ups in question answering, you should add alternate questions to capture different phrasings and enable multi-turn extraction to create follow-up prompts. These actions directly enhance the bot's ability to understand varied user input and maintain context. Other options either reduce flexibility or do not address the specific needs.

Answer

Increase the confidence threshold to 90% to ensure only high-confidence answers are returned.

Answer

Use the exact match only setting to ensure answers are precise.

Answer

Add more source documents to the knowledge base to cover additional topics.

Question 6

You are building an ASP.NET Core web app that must analyze the sentiment of user-submitted product reviews in real time. The app is deployed to an Azure App Service web app. You want to avoid managing API keys in code and prefer to use the app's managed identity for authentication to the Azure AI Language resource. What should you do to enable the app to call the sentiment analysis API securely?

Accepted Answer

Assign the Cognitive Services User role to the App Service's managed identity on the Language resource, and use DefaultAzureCredential in the app code.. The recommended secure approach is to use managed identity with Microsoft Entra ID authentication. Assigning the Cognitive Services User role to the App Service's managed identity grants the necessary permissions, and DefaultAzureCredential in the SDK automatically obtains a token. This eliminates the need to store or manage API keys in code, aligning with the scenario's requirement.

Answer

Configure the app to use the Language resource's endpoint and a SAS token generated from the resource's keys.

Answer

Store the Language resource's subscription key in Azure Key Vault and retrieve it at runtime using the app's managed identity.

Answer

Enable a system-assigned managed identity on the App Service and add the identity's object ID to the Language resource's access control list (ACL).

Question 7

A support organization uses Azure AI Language custom named entity recognition (custom NER) to extract product codes from warranty emails. The model performs well in production, but a new product line introduced codes formatted as two letters, a hyphen, and six digits, and the model misses them. You need the model to recognize the new format while keeping existing extraction quality. What should you do?

Accepted Answer

Add labeled utterances containing the new code format to the existing project, retrain, and review the evaluation metrics before redeploying.. The reliable way to extend a custom NER model to a new entity shape is to label representative utterances that contain that shape and retrain, then verify with evaluation metrics. This preserves the learned behavior on existing codes because the original labeled data remains in the project, while the new examples supply the boundary evidence the model needs for the two-letter, hyphen, six-digit pattern.

Answer

Increase the model's temperature setting so it generalizes to unseen code formats.

Answer

Create a new custom NER project dedicated to the new product line and route emails to it based on keyword rules.

Answer

Add the new product codes to a phrase list attached to the entity and redeploy the existing model.

Question 8

You are building a generative AI solution that uses Azure OpenAI function calling to let the model invoke backend APIs. During testing, the model sometimes invents parameter values that cause API errors. You need to make function invocation more reliable. What should you do?

Accepted Answer

Define clear function schemas with typed parameters, required fields, and descriptions, and validate arguments before executing the API call.. Reliable function calling depends on well-defined schemas and validation. Typed parameters, required fields, and descriptive names help the model map user intent to correct arguments, and validating before execution prevents invalid values from reaching the API. Higher temperature, oversized specifications, and parallel-call limits do not enforce argument correctness.

Answer

Set tool_choice to auto and increase the temperature to encourage more creative argument generation.

Answer

Disable parallel tool calls and force the model to call only one function per turn.

Answer

Include the full OpenAPI specification of every backend API in the system message.

Question 9

You need to build a solution that reads text from images in multiple languages, including Arabic and English, and translates the text into English. The solution must preserve the original layout as much as possible. Which combination of Azure AI services should you use?

Accepted Answer

Azure AI Document Intelligence Read and Azure AI Translator. Azure AI Document Intelligence Read (formerly Form Recognizer Read) is optimized for extracting text from images and documents while preserving the original layout, including bounding box coordinates for each text element. Azure AI Translator then translates the extracted text into English. This combination meets the requirement for multi-language OCR (including Arabic and English) and layout preservation.

Answer

Azure AI Document Intelligence Read and Azure AI Language

Answer

Azure AI Vision OCR and Azure AI Translator

Answer

Azure AI Speech and Azure AI Translator

Question 10

You are managing an Azure AI services resource that is used by several departments. The security team requires that you monitor the resource for unusual access patterns and receive alerts when the number of failed authentication attempts exceeds a threshold. You need to configure the appropriate Azure Monitor components. Which two actions should you take? (Choose two.)

Accepted Answer

Create an alert rule in Azure Monitor that triggers when the count of failed authentication events in the Log Analytics workspace exceeds a threshold.. To monitor failed authentication attempts, you must first enable diagnostic settings to collect logs into a Log Analytics workspace. Then, you can create an alert rule that queries those logs and triggers when the count of failed authentication events exceeds a threshold. The other options either address network security, provide general threat detection, or use an unrelated metric, so they do not meet the specific monitoring and alerting requirement.

Answer

Enable Azure Defender for AI services to detect anomalies and generate security alerts.

Answer

Create a metric alert on the TotalCalls metric for the Azure AI services resource.

Answer

Configure a private endpoint for the Azure AI services resource to restrict access to a virtual network.

Question 11

You are building a generative AI solution with Azure OpenAI Service. Prompts must be assembled from a system instruction, retrieved document chunks, and the user's question. You need a mechanism that automatically inserts the retrieved chunks into a designated placeholder in a prompt template before the request is sent to the model. What should you use?

Accepted Answer

Prompt flow with a Jinja prompt template node. Prompt flow's Jinja prompt template node is the supported way to author a reusable template whose placeholders are filled from flow inputs at runtime, which is exactly what injecting retrieved chunks requires. The other choices address safety filtering, authentication, or output length, none of which assemble prompt text. Using a template also keeps prompt logic versioned and testable within the flow.

Answer

A content filter configured on the Azure OpenAI deployment

Answer

A system-assigned managed identity on the Azure OpenAI resource

Answer

The max_tokens parameter on the chat completions request

Question 12

You are building a solution that uses Azure AI Language's sentiment analysis to monitor customer feedback. The feedback includes text in multiple languages, and you need to obtain sentiment scores at both the document level and the sentence level. Which API endpoint should you call?

Accepted Answer

POST /language/:analyze-text with kind set to "SentimentAnalysis" and include opinion mining.. The unified Azure AI Language endpoint /language/:analyze-text supports sentiment analysis when the kind parameter is set to SentimentAnalysis. It returns both document-level and sentence-level sentiment, and can optionally include opinion mining. This is the current recommended approach, replacing the older Text Analytics API endpoints. The other options either use legacy endpoints or specify incorrect task kinds.

Answer

POST /language/:analyze-text with kind set to "KeyPhraseExtraction" and include sentiment scores.

Answer

POST /text/analytics/v3.1/sentiment with the showStats parameter set to true.

Answer

POST /language/:analyze-conversations with kind set to "SentimentAnalysis".

Question 13

You need to build a solution that extracts the main topics discussed in recorded customer service calls. The audio is already transcribed to text, and you must return the most salient phrases without any predefined categories. Which Azure AI Language feature should you use?

Accepted Answer

Key phrase extraction. Key phrase extraction is the Azure AI Language feature designed to surface the main talking points in text without any predefined categories or training. It returns a list of salient phrases per document, which can be aggregated across call transcripts to reveal discussion themes. Custom classification needs labeled classes, entity recognition targets named entities rather than topics, and extractive summarization returns sentences instead of topic phrases.

Answer

Named entity recognition

Answer

Extractive summarization

Answer

Custom text classification

Question 14

Your company wants to build a custom generative AI model that generates architectural designs. The model should be trained on the company's proprietary dataset of floor plans and designs. Which Azure service should you use?

Accepted Answer

Azure Machine Learning. Azure Machine Learning is the correct service because it provides a comprehensive platform for training custom generative AI models using your own proprietary datasets. It supports deep learning frameworks like PyTorch and TensorFlow, enabling you to build, train, and deploy a custom generative model for architectural designs, whereas Azure OpenAI Service is limited to pre-trained models and fine-tuning, not custom training from scratch.

Answer

Azure OpenAI Service

Answer

Azure AI Vision

Answer

Azure AI Document Intelligence

Question 15

You are building an Azure OpenAI solution that must generate product descriptions from a small set of 40 curated examples that demonstrate your brand voice. You want the model to imitate the style without changing the model weights or incurring the cost of a fine-tuning job. What should you do?

Accepted Answer

Include several of the curated examples directly in the system and user messages of each chat completion request.. Few-shot prompting embeds a handful of curated examples in the prompt so the model mimics their tone, structure, and vocabulary on each call. Because the requirement is a small example set and no weight modification or fine-tuning cost, in-context examples are the correct mechanism. Sampling parameters and retrieval indexes do not substitute for style conditioning.

Answer

Set the temperature parameter to 2 and the top_p parameter to 0.1 on every request.

Answer

Upload the examples to an Azure AI Search index and enable semantic ranker on the index.

Answer

Create a fine-tuning job in Azure OpenAI Studio using the 40 examples and deploy the resulting custom model.