AI-102 Practice Exam 54 — 20 Questions

Question 1

Your organization has a large corpus of legal documents that need to be analyzed for specific clauses. You need to extract key information such as party names, dates, and monetary amounts. The solution must be able to handle varying document formats (PDF, Word, scanned images). Which combination of Azure AI services should you use?

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

Accepted Answer

Azure AI Document Intelligence and Custom Entity Extraction. Azure AI Document Intelligence (formerly Form Recognizer) is designed to extract text, structure, and key-value pairs from PDFs, Word documents, and scanned images using OCR and layout analysis. Combining it with Custom Entity Extraction (via Azure AI Language's custom NER) allows you to identify domain-specific entities like party names, dates, and monetary amounts across varying formats. This pairing directly addresses the need for both document parsing and tailored entity recognition.

Answer

Azure AI Computer Vision and Custom Entity Extraction

Answer

Azure AI Translator and Custom Entity Extraction

Answer

Azure AI Speech and Custom Entity Extraction

Question 2

Your organization is using Azure AI Document Intelligence to process a mix of invoices and purchase orders. You need to ensure that documents are correctly classified before extraction. Which THREE steps should you take?

Accepted Answer

Create a custom classification model in Document Intelligence. Azure AI Document Intelligence requires you to create a custom classification model to distinguish between document types like invoices and purchase orders. This model is built by training on labeled samples, enabling it to assign a document type before extraction. Without a custom classifier, the service cannot automatically route documents to the appropriate extraction model.

Answer

Train the classification model with one sample per type

Answer

Use the prebuilt invoice and purchase order models for classification

Question 3

You need to deploy a generative AI model that can generate images from text descriptions. Which Azure service should you use?

Accepted Answer

Azure OpenAI Service. Azure OpenAI Service provides access to advanced generative AI models like DALL-E, which are specifically designed to generate images from natural language text descriptions. This service offers pre-trained models that can create high-quality images based on textual prompts, making it the correct choice for this task.

Answer

Azure Machine Learning

Answer

Azure AI Vision

Answer

Azure AI Language

Question 4

You are a machine learning engineer at a large retail company. The company has thousands of product descriptions that need to be updated regularly. They currently use a manual process. You propose using Azure OpenAI to generate new descriptions based on product attributes. You have a dataset of existing product descriptions and attributes stored in an Azure SQL Database. The solution must be cost-effective, scalable, and must not require retraining the model. You need to design the solution. You have the following options:

Option A: Use Azure OpenAI with few-shot learning by including examples in the prompt for each product. Deploy the model on an Azure Kubernetes Service (AKS) cluster for high throughput.

Option B: Use Azure OpenAI with prompt templates that include product attributes and call the API for each product. Use Azure Logic Apps to orchestrate the workflow and store results back to Azure SQL Database.

Option C: Fine-tune a custom model on the existing product descriptions and deploy it as a managed endpoint. Use Azure Data Factory to batch process all products.

Option D: Use Azure OpenAI with the batch API to generate descriptions for all products at once, using a single prompt that lists all products and attributes. Store the batch output in Azure Blob Storage and then import into Azure SQL Database.

Which option should you choose?

Accepted Answer

Option B. (Azure Logic Apps) is the correct choice. It uses Azure OpenAI with prompt templates that insert product attributes, making individual API calls per product. This approach is scalable because Azure Logic Apps can handle high volumes with built-in retry and concurrency, and it is cost-effective as you only pay per API call and execution. It does not require model retraining. In contrast, Option A (AKS) introduces unnecessary infrastructure complexity; Option C (fine-tuning) requires retraining; and Option D (batch API) risks exceeding prompt size limits and is less suitable for incremental updates.

Answer

Option C

Answer

Option D

Answer

Option A

Question 5

You deploy a custom vision model for defect detection on a manufacturing line. The model runs on an Azure IoT Edge device. You notice that inference latency is too high for real-time detection. Which action should you take to reduce latency?

Accepted Answer

Convert the model to TensorFlow and use the Azure IoT Edge Deep Learning module with hardware acceleration. Converting the model to TensorFlow enables compatibility with the Azure IoT Edge Deep Learning module, which can leverage hardware acceleration (e.g., Intel Movidius or NVIDIA GPUs) to significantly reduce inference latency. This approach keeps inference on the edge device, avoiding network round-trips, and optimizes the model for real-time defect detection.

Answer

Move inference to Azure Functions in the cloud

Answer

Retrain the model with more defect images

Answer

Increase the resolution of input images

Question 6

Your organization uses Microsoft 365 Copilot. You want to ensure that Copilot only uses data from your Microsoft 365 tenant and does not access external sources. Which setting should you configure?

Accepted Answer

Configure Copilot to use only Microsoft Graph data.. Configuring Copilot to use only Microsoft Graph data ensures that the AI model retrieves content exclusively from your Microsoft 365 tenant (e.g., emails, documents, calendar events) via Microsoft Graph APIs. This setting explicitly restricts Copilot from querying external sources like the public web or third-party services, aligning with the requirement to keep data within the tenant boundary. Option D is incorrect because disabling Bing search integration only prevents web search queries, but does not block other external data sources such as third-party connectors or public Microsoft Graph endpoints. To fully restrict Copilot to tenant data, you must configure the Microsoft Graph-only setting.

Answer

Disable 'Allow Copilot to use external data' in the Copilot settings.

Answer

Enable content filtering for Copilot.

Answer

Disable the Bing search integration in the Microsoft 365 admin center.

Question 7

You are building a knowledge mining solution to extract key information from handwritten forms. The forms contain checkboxes, signatures, and handwritten text. Which Azure AI service should you use?

Accepted Answer

Azure AI Document Intelligence layout model. Azure AI Document Intelligence's layout model is designed to extract text, tables, checkboxes, signatures, and structure from documents, including handwritten forms. It combines OCR with deep learning models to understand the spatial relationships between elements, making it the correct choice for this scenario.

Answer

Azure AI Language

Answer

Azure AI Speech

Answer

Azure AI Vision OCR

Question 8

You are building an agentic solution using Microsoft Semantic Kernel. The agent must autonomously decide when to call an external API to fetch real-time data. You want to minimize token usage and avoid unnecessary API calls. Which planner configuration should you use?

Accepted Answer

Use an AutoInvoke kernel with a greedy action planner. An AutoInvoke kernel with a greedy action planner enables the agent to make step-by-step decisions about which function to invoke next based on the immediate context. This minimizes token consumption by forgoing exhaustive plan generation and only triggering the external API when the current step requires it. In contrast, SequentialPlanner generates a complete plan upfront, potentially including unnecessary API calls, and manual or parallel planners either lack autonomy or increase token overhead.

Answer

Use a SequentialPlanner with a stepwise strategy and explicit function parameter constraints

Answer

Use a ManualInvoke kernel with a sequential planner

Answer

Use a ParallelPlanner with a function-calling model

Question 9

You are building a solution to extract key phrases from customer reviews using Azure AI Language. 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 return the main talking points or important terms from unstructured text, such as customer reviews. Azure AI Language's Key Phrase Extraction API analyzes the text structure and linguistic patterns to surface the most relevant phrases, which directly addresses the requirement to extract key phrases from reviews.

Answer

Sentiment Analysis

Answer

Language Detection

Answer

Named Entity Recognition

Question 10

A healthcare organization is deploying an Azure AI Document Intelligence solution to extract medical record data. The solution must comply with HIPAA and process sensitive patient data. The data must be encrypted at rest and in transit, and access must be audited. The solution will be used by multiple departments, each requiring different levels of access. Which combination of Azure services should the architect recommend?

Accepted Answer

Azure AI Document Intelligence with private endpoints, managed identity authentication, Azure Storage with customer-managed keys (CMK), and Azure RBAC for access control.. It ensures HIPAA compliance by using private endpoints to keep traffic within the Azure backbone network, managed identity for secure authentication without storing credentials, customer-managed keys (CMK) for encryption at rest with full control over key rotation, and Azure RBAC to enforce least-privilege access across departments. This combination addresses encryption in transit (private endpoint + HTTPS), encryption at rest (CMK), and audited access (RBAC + Azure Monitor).

Answer

Azure AI Document Intelligence with public endpoint, Azure AD authentication, and Azure Storage with customer-managed keys (CMK).

Answer

Azure AI Document Intelligence with public endpoint, Azure AD authentication, and Azure Storage with encryption at rest using Microsoft-managed keys.

Answer

Azure AI Document Intelligence with service endpoints, shared access signature (SAS) tokens, and Azure Storage with encryption at rest using Microsoft-managed keys.

Question 11

Your organization is implementing a knowledge mining solution for a research institute that needs to extract chemical compound names and reactions from scientific articles in PDF format. The solution must use a custom model because the scientific terminology is not covered by built-in skills. You have trained a custom model using Azure AI Language's custom entity recognition (NER) and deployed it as a REST endpoint. You are using Azure AI Search with a skillset. How should you integrate the custom NER model into the enrichment pipeline?

Accepted Answer

Create a custom skill that calls the custom NER endpoint and map the output to the index fields.. Custom NER models must be integrated into the enrichment pipeline via a custom skill that calls the model's REST endpoint and maps the extracted entities to index fields. Built-in Entity Recognition skills cannot use custom models (so C is wrong). LUIS is designed for language understanding, not custom NER (so B is wrong). Indexers cannot directly call external APIs; they rely on skills in the skillset (so D is wrong).

Answer

Use a Language Understanding (LUIS) app to extract entities and call it from a custom skill.

Answer

Use the built-in Entity Recognition skill and configure it with your custom model's endpoint.

Answer

Configure the indexer to call the custom NER endpoint directly during indexing.

Question 12

An organization is deploying a conversational AI solution using Azure OpenAI. They want to ensure the model's responses are grounded in their own knowledge base documents to reduce hallucinations. Which approach should they implement?

Accepted Answer

Integrate Azure Cognitive Search for retrieval-augmented generation (RAG). Retrieval-Augmented Generation (RAG) with Azure Cognitive Search allows the model to dynamically retrieve relevant chunks from the organization's knowledge base documents at inference time. This grounds responses in authoritative, up-to-date content, directly reducing hallucinations by providing factual context rather than relying solely on the model's parametric memory.

Answer

Fine-tune the model on the knowledge base documents

Answer

Implement Azure AI Content Safety filters

Answer

Use prompt engineering to instruct the model to only use the knowledge base

Question 13

You are designing a generative AI solution using Azure OpenAI Service. The solution must support multiple languages and provide consistent quality across languages. Which THREE actions should you take?

Accepted Answer

Use a model that supports multiple languages (e.g., GPT-4). GPT-4 is a multilingual model pre-trained on diverse language corpora, enabling it to generate coherent and contextually appropriate responses across many languages without additional fine-tuning. This ensures consistent quality by leveraging the model's inherent cross-lingual capabilities, which is essential for a generative AI solution that must support multiple languages.

Answer

Fine-tune the model on a dataset of a single language

Answer

Set the temperature to 0 for all requests

Question 14

You are designing a solution that reads handwritten notes from patient intake forms. The solution must handle various handwriting styles. Which Azure AI capability should you use?

Accepted Answer

Azure AI Document Intelligence Read model. Azure AI Document Intelligence Read model is specifically designed to extract printed and handwritten text from documents, including patient intake forms. It uses advanced OCR capabilities optimized for varied handwriting styles and document layouts, making it the correct choice for this scenario.

Answer

Azure AI Custom Vision

Answer

Azure AI Vision OCR

Answer

Azure AI Language

Question 15

You are deploying a generative AI model using Azure AI Foundry. The model must be accessible only from a specific virtual network. Additionally, you need to monitor all API calls for auditing. Which two configurations are required? (Choose two.)

Accepted Answer

Enable diagnostic settings to send logs to a Log Analytics workspace.. Enabling diagnostic settings to send logs to a Log Analytics workspace captures all API call details (e.g., request URI, response status, caller IP) for auditing and monitoring. This is the standard Azure method for collecting resource-level logs, and it works with Azure AI Foundry deployments to meet compliance and security requirements.

Answer

Assign a managed identity to the model deployment.

Answer

Enable public network access from selected IP addresses.

Answer

Configure CORS to allow only the VNet's domain.

Question 16

Your organization is deploying an agentic solution using Microsoft Copilot Studio. The agent must be able to escalate to a human agent when it cannot resolve a user's request. You need to ensure that the escalation includes the full conversation history. What should you configure?

Accepted Answer

Add a 'Transfer conversation' action and set it to include the full transcript. The 'Transfer conversation' action in Microsoft Copilot Studio is specifically designed to hand off the conversation to a human agent, and it includes an option to pass the full conversation transcript. This ensures the human agent has complete context, which is required for a seamless escalation. The other options do not provide this capability.

Answer

Add an 'End conversation' action and configure a fallback

Answer

Add a 'Create a ticket' action in the topic

Answer

Add a 'Start a new topic' action with context variables

Question 17

A company uses Microsoft Copilot Studio to create an agent that helps employees schedule meetings. The agent must access the user's calendar to find free time slots and book meetings. The agent should only work for users who have granted consent. Which authentication and authorization approach should be used?

Accepted Answer

Configure OAuth 2.0 authentication with Microsoft Entra ID and request delegated permissions for Microsoft Graph.. The agent needs to act on behalf of a signed-in user (delegated identity) to access their calendar. OAuth 2.0 with Microsoft Entra ID and delegated permissions for Microsoft Graph allows the agent to request only the scopes (e.g., Calendars.ReadWrite) that the user has consented to, ensuring the agent operates within the user's granted permissions.

Answer

Use certificate-based authentication for the agent.

Answer

Use API key authentication to call Microsoft Graph.

Answer

Use OAuth 2.0 client credentials flow with application permissions.

Question 18

You are deploying a Custom Vision model to a production environment. The model must handle 100 predictions per second with low latency. Which deployment option should you choose?

Accepted Answer

Use a paid tier prediction endpoint with sufficient capacity.. A paid tier prediction endpoint in Azure Custom Vision is designed to handle production-scale workloads with dedicated compute resources, supporting up to 100 predictions per second with low latency. The Free tier is rate-limited and cannot sustain this throughput, while exporting as a Docker container introduces additional overhead and scaling complexity that may not guarantee the required latency or throughput without manual orchestration.

Answer

Use the Free tier prediction endpoint.

Answer

Export the model as a Docker container and run it on Azure Container Instances.

Answer

Use the Training API to make predictions.

Question 19

Your team is developing a chatbot using Azure AI Bot Service with Language Understanding (LUIS). You need to improve intent recognition for user queries that contain typos. What should you recommend?

Accepted Answer

Enable Bing Spell Check in the LUIS app settings. Enabling Bing Spell Check in the LUIS app settings allows the service to automatically correct typos in user utterances before they are processed for intent recognition. This built-in feature integrates directly with LUIS at the endpoint, correcting misspelled words to improve the accuracy of intent and entity extraction without requiring manual data augmentation or external services.

Answer

Add synonym lists for common misspellings

Answer

Use Azure Cognitive Search to correct typos

Answer

Train the model with many examples containing typos

Question 20

Refer to the exhibit. You deployed a Conversational Language Understanding (CLU) project. A user says 'hi, where is my order?' The model returns a single intent 'Greeting' with confidence 0.85. You need the model to detect both intents. What should you change?

Accepted Answer

Set 'multipleIntents' to true.. The Conversational Language Understanding (CLU) service supports multi-intent detection only when the 'multipleIntents' flag is explicitly set to true in the project settings. By default, CLU returns only the highest-confidence intent; enabling this flag allows the model to return all intents whose confidence exceeds the threshold, enabling detection of both 'Greeting' and 'OrderStatus' from a single utterance.

Answer

Lower the confidenceThreshold to 0.5.

Answer

Add more utterances to the 'OrderStatus' intent.

Answer

Change the project kind to 'Orchestration'.