AI-102 Practice Test 37 — 15 Questions

Question 1

Refer to the exhibit. You deploy this ARM template to create an agent. The agent uses a user-assigned managed identity to call an external weather API. The deployment succeeds but the agent fails to authenticate to the weather API. What is the most likely reason?

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

Accepted Answer

The external weather API is not configured to accept tokens from the managed identity's tenant.. The agent uses a user-assigned managed identity to authenticate to an external weather API. Managed identities provide tokens that are valid only within the Microsoft Entra ID (formerly Azure AD) tenant where the identity is registered. For the agent to successfully authenticate, the external weather API must be configured as an application in that same tenant and trust tokens issued by that tenant. Option D correctly identifies that the most likely reason for authentication failure is that the external weather API is not configured to accept tokens from the managed identity's tenant, meaning the API does not trust the token issuer.

Answer

The resourceId for the managed identity is incorrect.

Answer

The model provider 'AzureAI' should be 'AzureOpenAI'.

Answer

The URL parameter is missing the API version.

Question 2

You need to restrict access to an Azure AI Language resource so that only a specific virtual network can call the endpoint. Which configuration should you use?

Accepted Answer

Enable a service endpoint or private endpoint for the resource. Azure AI Language resources can be isolated to a specific virtual network by enabling either a service endpoint (via the Microsoft.CognitiveServices service tag) or a private endpoint (using Azure Private Link). This configuration ensures that only traffic originating from the designated VNet can reach the resource's endpoint, effectively blocking all public internet access. Service endpoints provide a direct, optimized route from the VNet to the resource, while private endpoints assign a private IP from the VNet to the resource, making it accessible only within the VNet.

Answer

Rotate the shared access keys

Answer

Assign a managed identity to the resource

Answer

Configure an IP firewall rule with the VNet's public IP range

Question 3

You are designing a solution that uses Azure AI Document Intelligence to extract data from invoices. The invoices are in various formats (PDF, TIFF, and JPEG) and languages. You need to ensure high accuracy for extraction. Which approach should you take?

Accepted Answer

Use a custom extraction model trained on a sample set of invoices covering all formats and languages.. Azure AI Document Intelligence’s custom extraction models are trained on your specific invoice samples, enabling the model to learn the unique layouts, fields, and languages present across PDF, TIFF, and JPEG formats. This approach directly addresses the need for high accuracy on varied formats and languages, as the model adapts to the exact patterns in your data rather than relying on a generic prebuilt model or brittle post-processing.

Answer

Use the prebuilt invoice model and configure language detection.

Answer

Use Azure AI Vision OCR to extract all text and then parse using regular expressions.

Answer

Convert all invoices to a single format (e.g., PDF) before processing.

Question 4

You are deploying a custom Named Entity Recognition (NER) model using Azure AI Language. You have 500 labeled documents. After training, the model shows high precision but low recall. Which action is most likely to improve recall?

Accepted Answer

Add more labeled examples covering the missed entities. Adding more labeled examples that cover the missed entities directly addresses the root cause of low recall: the model has not seen enough representative patterns for those entities during training. In Azure AI Language custom NER, the model learns to recognize entities based on the labeled data; insufficient or imbalanced examples for certain entity types cause the model to fail to identify them, lowering recall. Enriching the training set with diverse examples of the underperforming entities gives the model more opportunities to learn their variations, thereby improving recall without sacrificing precision.

Answer

Switch to Conversational Language Understanding

Answer

Reduce the confidence threshold for entity extraction

Answer

Increase the number of training epochs

Question 5

You are building a custom named entity recognition (NER) model using Azure AI Language. After labeling 200 documents, you train the model and achieve 85% precision but only 60% recall. Which action is most likely to improve recall?

Accepted Answer

Increase the number of labeled documents, especially those containing the target entities. Low recall in a custom NER model typically indicates that the model is failing to identify many instances of the target entities. Increasing the number of labeled documents, especially those containing the target entities, provides more positive examples for the model to learn from, directly improving its ability to recognize those entities and thus boosting recall.

Answer

Lower the confidence threshold

Answer

Increase the training hours

Answer

Switch to a different Azure AI Language feature

Question 6

Refer to the exhibit. You called the Named Entity Recognition API on a document. Which entity type is "Seattle"?

Accepted Answer

Location. The Named Entity Recognition (NER) API in Azure AI Language identifies 'Seattle' as a Location entity because it is a recognized geographical place. The API uses a pre-trained model that categorizes entities into types such as Location, Person, Organization, etc., and 'Seattle' falls under the Location type based on its semantic context in the document.

Answer

Organization

Answer

Person

Answer

City

Question 7

You are building a generative AI application using Azure OpenAI Service. The application must provide citations for answers retrieved from a set of documents. You need to ensure that each answer includes a reference to the source document. Which configuration should you use?

Accepted Answer

Use Azure OpenAI On Your Data with the 'include citations' option. Azure OpenAI On Your Data provides a built-in 'include citations' feature that automatically retrieves and appends source document references to the generated answer. This configuration leverages the underlying search index to map each response segment back to the original document, ensuring compliance with citation requirements without custom development.

Answer

Add a system message requesting citations

Answer

Implement a custom prompt flow with citation logic

Answer

Fine-tune the model to include citations

Question 8

Your Azure AI Search index stores customer support tickets. You need to implement a search feature that returns semantically similar results even if the query uses different wording. Which configuration should you enable?

Accepted Answer

Enable semantic search and configure a semantic configuration. Semantic search in Azure AI Search uses deep neural networks to understand the intent and context of a query, returning results that are semantically similar even when the wording differs. By enabling semantic search and configuring a semantic configuration, you define which fields are used for summarization and ranking, which directly addresses the requirement for meaning-based matching rather than keyword matching.

Answer

Use simple query parsing with searchMode=any

Answer

Add a synonym map with custom entries

Answer

Enable fuzzy search on the index

Question 9

You have an Azure AI Search skillset defined as shown in the exhibit. When you run the indexer, the enrichment pipeline produces outputs but no entities are extracted. The source documents are in English and contain clear organization and person names. What is the most likely cause?

Accepted Answer

The '/document/content' field is an array, but the skill expects a string.. The most likely cause is that the '/document/content' field is an array, but the Entity Recognition skill expects a string input. In Azure AI Search, if the source field is an array, the skill cannot process it directly, resulting in no entities being extracted even though the documents contain clear organization and person names.

Answer

The skill output is not mapped to the index.

Answer

The skills are in the wrong order.

Answer

The documents are not in English.

Question 10

Which THREE are valid parameters when calling the Azure OpenAI Service chat completions API?

Accepted Answer

messages. The `messages` parameter is required in the Azure OpenAI Service chat completions API call. It defines the conversation history and user input as an array of message objects, each with a `role` (system, user, assistant) and `content`. Without this parameter, the API cannot determine the context or prompt for generating a response.

Answer

index_name

Answer

embedding_model

Question 11

You are building an application that processes scanned invoices to extract key fields such as total amount, invoice date, and vendor name. The application uses Azure AI Document Intelligence. You need to ensure high accuracy for field extraction without manual labeling. Which feature should you use?

Accepted Answer

Use the General Document model. The General Document model in Azure AI Document Intelligence can extract common fields like total amount, invoice date, and vendor name from invoices without requiring any labeled training data. While a custom neural model would offer higher accuracy, it requires manual labeling of sample documents, which contradicts the requirement of no manual labeling. Therefore, the General Document model is the appropriate choice.

Answer

Use the Read API

Answer

Use a custom neural model

Answer

Use the Layout API

Question 12

Based on the exhibit, which entity should you focus on improving by adding more labeled examples?

Accepted Answer

ProductName. The exhibit shows that ProductName has a recall of 0.65, which is lower than the recall for Date (0.98) and OrderNumber (0.99). Low recall indicates that the model is missing many true instances of ProductName. Adding more labeled examples specifically for ProductName will help the model learn its patterns better, improving recall and overall performance. This aligns with the practice of iterative model improvement in custom entity extraction within Azure AI Language.

Answer

Date

Answer

OrderNumber

Answer

All entities need improvement.

Question 13

Which TWO capabilities are provided by Azure AI Language's pre-built entity recognition?

Accepted Answer

Identifying names of people. Azure AI Language's pre-built entity recognition includes a category for 'Person' that identifies names of people in text. This is a standard named entity recognition (NER) capability that extracts entities like individuals' names without requiring custom model training.

Answer

Identifying domain-specific medical terms

Answer

Extracting key phrases from text

Answer

Determining overall sentiment of the text

Question 14

A company is building an agentic solution using Azure AI Agent Service. The agent needs to execute a Power Automate flow when a user requests a vacation approval. Which action type should the developer add to the agent's action definition?

Accepted Answer

powerAutomateFlow. The Azure AI Agent Service supports a dedicated 'powerAutomateFlow' action type that directly triggers a Power Automate flow when invoked by the agent. This is the correct choice because the requirement explicitly states the agent must execute a Power Automate flow for vacation approval, and this action type is purpose-built for that integration without needing custom HTTP or API definitions.

Answer

httpRequest

Answer

openApi

Answer

function

Question 15

Your team is implementing a knowledge mining solution using Azure AI Search with custom skills. The custom skill, deployed as an Azure Function, calls a third-party API to enrich documents. You notice that some documents fail enrichment with HTTP 429 (too many requests) errors. You need to ensure all documents are enriched without losing data. What should you do?

Accepted Answer

Configure the custom skill to execute in batch mode and set a retry policy on the indexer. Configuring the custom skill to execute in batch mode reduces the number of HTTP requests to the third-party API by processing multiple documents per invocation, while setting a retry policy on the indexer ensures that failed documents due to transient HTTP 429 errors are automatically retried. This combination prevents data loss by not skipping documents and by handling rate-limiting gracefully.

Answer

Increase the number of partitions in the Azure AI Search service

Answer

Enable indexer error handling to skip failed documents

Answer

Scale out the Azure Function to multiple instances