Microsoft

AI-103 Free Practice Questions — Page 6

Question 27

HOTSPOT You are building a solution that students will use to find references for essays. You use the following code to start building the solution. For each of the following statements, select Yes is the statement is true. Otherwise, select No. NOTE: Each correct selection is worth one point.

Illustration for AI-103 question 27 Illustration for AI-103 question 27
Show Answer
Correct Answer: 1. No 2. No 3. Yes
Explanation:
The code calls linked-entity recognition, not language detection. A linked entity’s `url` points to a source page, not necessarily a Bing search. Its `matches` include offsets identifying where the entity appears in the document.

Question 28

You have a chat app in a Microsoft Foundry project and an Azure AI Search vectorized index. You need to connect to the index to meet the following requirements: Complex questions must retrieve information from multiple chunks. Multi-turn conversations must influence retrieval planning. Retrievals must run in parallel to reduce latency. Which retrieval approach should you use?

A. iterative retrieval
B. agentic Retrieval Augmented Generation (RAG)
C. chain of thought
D. classic Retrieval Augmented Generation (RAG)
Show Answer
Correct Answer: B
Explanation:
Agentic Retrieval Augmented Generation (RAG) is designed to decompose complex queries into multiple subqueries, use conversation context to plan retrieval across turns, and execute retrievals in parallel to reduce latency. Classic RAG performs a single retrieval step, iterative retrieval is sequential, and chain of thought is a reasoning/prompting technique rather than a retrieval approach.

Question 28

You are building an app that will include one million scanned magazine articles. Each article will be stored as an image file. You need to configure the app to extract text from the images. The solution must minimize development effort. What should you include in the solution?

A. Azure Document Intelligence in Foundry Tools
B. the Read API in Azure Vision in Foundry Tools
C. Azure Vision in Foundry Tools Image Analysis
D. Azure Language in Foundry Tools
Show Answer
Correct Answer: A
Explanation:
Use Azure Document Intelligence’s prebuilt Read capability. Magazine articles are text-heavy documents, and Document Intelligence is suited to extracting text from scanned documents stored as images without requiring a custom model.

Question 29

HOTSPOT - You have a Microsoft Foundry project that contains a deployed chat model. You have a Python service that sends API requests to the model. The service is integrated with an automated validation system that compares generated outputs against approved response patterns. Stakeholders report that small wording differences are causing validation mismatches. You need to update the request parameters to improve output stability. The solution must maximize reasoning quality. How should you complete the Python code? To answer, select the appropriate options in the answer area. NOTE: Each correct selection is worth one point.

Illustration for AI-103 question 29
Show Answer
Correct Answer: Temperature: 0 Effort: high
Explanation:
Setting temperature to 0 minimizes randomness and improves output consistency for automated validation. Setting reasoning effort to high maximizes reasoning quality.

Question 29

DRAG DROP You are building an app that will scan confidential documents and use the Azure Language in Foundry Tools service to analyze the contents. You provision a Microsoft Foundry Service resource. You need to ensure that the app can make requests to the Azure Language in Foundry Tools service endpoint. The solution must ensure that confidential documents remain on-premises. Which three actions should you perform in sequence? To answer, move the appropriate actions from the list of actions to the answer area and arrange them in the correct order.

Illustration for AI-103 question 29
Show Answer
Correct Answer: 1. Provision an on-premises Kubernetes cluster that has internet connectivity. 2. Pull an image from the Microsoft Container Registry (MCR). 3. Run the container and specify the Azure AI resource’s API key and endpoint URL.
Explanation:
An on-premises Language container keeps document processing local. It needs internet access to the Azure resource for billing, and its image is distributed through MCR.

Question 30

You have a customer support agent that uses the Microsoft Foundry Agent Service. Sometimes, customers return to a session days later to continue the same support case, and the agent must resume with the full historical context. The agent must provide the following: Multi-turn continuity within the session Cross-session continuity for the same case Access to the full interaction history, including user messages, agent messages, tool calls, and tool outputs You need to ensure that the agent automatically reloads the complete history on each new turn. What should you do?

A. Create and reuse a conversation by storing the conversation’s ID and supplying the ID on subsequent requests.
B. Persist only the final model response stored in the client application and prepend the response to future prompts.
C. Enable memory summarization on the agent definition to persist the context automatically.
Show Answer
Correct Answer: A
Explanation:
Reusing the same conversation (thread) ID allows the Foundry Agent Service to automatically load the complete server-side conversation state on each turn, including user and agent messages, tool calls, and tool outputs. This provides both multi-turn continuity and cross-session continuity. Persisting only the final response loses the detailed interaction history, and memory summarization compresses context rather than restoring the full history.

Question 30

You have an Azure subscription that contains a Microsoft Foundry Service resource named CSAccount1 and a virtual network named VNet1. CSAaccount1 is connected to VNet1. You need to ensure that only specific resources can access CSAccount1. The solution must meet the following requirements: • Prevent external access to CSAccount1. • Minimize administrative effort. Which two actions should you perform? Each correct answer presents part of the solution. NOTE: Each correct answer is worth one point.

A. In CSAccount1, modify the virtual network settings.
B. In VNet1, create a virtual subnet.
C. In VNet1, enable a service endpoint for CSAccount1.
D. In CSAccount1, configure the Access control (IAM) settings.
E. In VNet1, modify the virtual network settings.
Show Answer
Correct Answer: A, C
Explanation:
Configure CSAccount1’s virtual network settings to allow access only from the specified virtual network, and enable the Microsoft.CognitiveServices service endpoint on VNet1. This restricts access to the selected network without requiring more complex network controls.

Question 31

You have a Microsoft Foundry project that contains a prompt agent used by a customer support web app. The agent is invoked from a Python service that does NOT run in the Foundry portal. You need to implement end-to-end tracing to capture latency breakdowns and exceptions across agent runs. Which two components can you use? Each correct answer presents a complete solution. NOTE: Each correct selection is worth one point.

A. a Log Analytics workspace
B. Application Insights
C. OpenTelemetry
D. the Azure Monitor Agent
E. Microsoft Sentinel
Show Answer
Correct Answer: B, C
Explanation:
Application Insights provides distributed tracing, telemetry collection, latency visualization, and exception monitoring. OpenTelemetry can instrument the external Python service and agent interactions to generate end-to-end traces that are exported to a backend such as Application Insights. Log Analytics is a data store rather than the tracing component, Azure Monitor Agent collects VM/host telemetry, and Microsoft Sentinel is a SIEM, not an application tracing solution.

Question 31

HOTSPOT You are developing an app that will use the Azure Vision in Foundry Tools API to analyze an image. You need configure the request that will be used by the app to identify whether an image is clipart or a line drawing. How should you complete the request? To answer, select the appropriate options in the answer area. NOTE: Each correct selection is worth one point.

Illustration for AI-103 question 31
Show Answer
Correct Answer: HTTP method: POST visualFeatures: imageType
Explanation:
The analyze endpoint accepts an image in a POST request. The imageType visual feature identifies clipart and line drawings.

Question 32

DRAG DROP - You have a Microsoft Foundry project that contains an agent used by the financial analysts at your company. You need to optimize the agent workflow by providing additional data access and processing capabilities. The solution must meet the following requirements: Ensure that the agent can perform calculations during conversations. Ensure that the agent can access up-to-date information from public websites. Ensure that the agent can retrieve information from documents uploaded directly to the agent. What should you use for each requirement? To answer, drag the appropriate tools to the correct requirements. Each tool may be used once, more than once, or not at all. You may need to drag the split bar between panes or scroll to view content. NOTE: Each correct selection is worth one point.

Illustration for AI-103 question 32
Show Answer
Correct Answer: Access up-to-date information from public websites: Grounding with Bing Search Perform calculations during conversations: Code interpreter Retrieve information from documents uploaded directly to the agent: File search
Explanation:
Code Interpreter executes code for calculations, Grounding with Bing Search provides current public web data, and File Search indexes and retrieves content from uploaded documents.

$19

Get all 147 questions with detailed answers and explanations

  • Instant download HTML + PDF delivered the moment payment clears.
  • Secure Stripe checkout we never see or store your card details.
  • 7-day refund if files are defective see our refund policy.