Home / Microsoft / AI-103
Microsoft · AI-103

AI-103 Exam Practice Questions

Microsoft Certified: Azure AI Apps and Agents Developer Associate

AI-103 English PDF practice questions: 161 questions in source order, with options supported by the source format, answers and available explanations. Access covers this exam only. One-time payment; no automatic renewal.

Exam overview

For Azure AI developers building and operating AI applications and agents with Microsoft Foundry.

Exam code
AI-103
Official exam / credential
Microsoft Certified: Azure AI Apps and Agents Developer Associate
Exam format
Proctored assessment; interactive items may be included
Exam duration
120 minutes
Official exam languages
English, Simplified Chinese, Traditional Chinese, French, German, Japanese, Korean, Italian, Portuguese (Brazil), Spanish

Official exam languages and practice-question file languages are listed separately. Confirm the exam version and available languages when booking with the provider.

Official sources: Provider reference
Information checked: 2026-10-20

Supported languages

  • English
  • Simplified Chinese
  • Traditional Chinese
Try before you buy

First 20 practice questions

161 total questions

Questions follow the source order. Expand each answer to see its explanation.

Disclaimer: All questions on ExamPico are compiled from internet sources and are provided for study reference only.

Question 11

Question#11Topic1

HOTSPOT -
You have a Microsoft Foundry project that contains an agent named PaymentAgent.
PaymentAgent includes a function tool that issues customer refunds by using an external API.
You are creating a workflow in YAML.
You need to ensure that the workflow pauses for human approval and continues with the refund step only after approval is granted.
How should you complete the workflow definition? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
Question illustration

Show answer

Answer

AA

Question 12

Question#12Topic1

You have an Azure Speech in Foundry Tools resource that hosts a custom speech to text model deployed to a custom endpoint. An agent uses the endpoint to perform real-time speech recognition.
You are approaching the expiration date of the custom speech to text model.
What is the expected behavior when the model expires?

  1. A. Speech recognition requests will return a 4xx error until a new custom model is deployed.
  2. B. Speech recognition requests will continue to use the expired custom model until the model is removed manually.
  3. C. Speech recognition requests will fall back to the most recent base model for the same locale.
  4. D. The custom model will be deleted automatically when the model expires.
Show answer and explanation

Answer

C

Explanation

Azure AI Search (Azure Cognitive Search) indexes PDF content from Azure Blob Storage using the Blob indexer and makes it available for retrieval. For grounding an agent on internal product PDF sheets, Azure AI Search provides indexing, enrichment (OCR), and semantic/vector retrieval for RAG scenarios. See: https://learn.microsoft.com/azure/search/search-howto-indexing-azure-blob-storage and https://learn.microsoft.com/azure/search/overview

Question 13

Question#13Topic1

You have a Microsoft Foundry project that contains a model deployment.
You have an application that calls the deployment by using the Azure OpenAI v1 API and DefaultAzureCredential.
The developers at your company receive HTTP 403 errors when they send inference requests, even after running az login.
You need to ensure that the developers can perform model inference. The solution must follow the principle of least privilege.
Which role-based access control (RBAC) role should you assign to the developers?

  1. A. Cognitive Services User
  2. B. Cognitive Services OpenAI User
  3. C. Contributor
  4. D. Cognitive Services Data Reader
Show answer and explanation

Answer

C

Explanation

Azure AI Search (Azure Cognitive Search) indexes PDF content from Azure Blob Storage using the Blob indexer and makes it available for retrieval. For grounding an agent on internal product PDF sheets, Azure AI Search provides indexing, enrichment (OCR), and semantic/vector retrieval for RAG scenarios. See: https://learn.microsoft.com/azure/search/search-howto-indexing-azure-blob-storage and https://learn.microsoft.com/azure/search/overview

Question 14

Question#14Topic1

You have a Microsoft Foundry project that contains an agent. The agent has a Model Context Protocol (MCP) tool that queries a knowledge base stored in Azure AI Search.
Some agent runs return answers from the base model without invoking the knowledge base, which results in responses without grounded citations.
You are provided with the following code snippet that runs the agent.
Question illustration
You need to add the correct tool _choice parameter to the code to deterministically force the agent to invoke the MCP tool on each run.
What should you add?

  1. A. tool_choice={“required”}
  2. B. tool_choice={“auto”}
  3. C. tool_choice={“type”:“knowledge_base”}
  4. D. tool_choice ={“type”:“mcp”}
Show answer and explanation

Answer

C

Explanation

Azure AI Search (Azure Cognitive Search) indexes PDF content from Azure Blob Storage using the Blob indexer and makes it available for retrieval. For grounding an agent on internal product PDF sheets, Azure AI Search provides indexing, enrichment (OCR), and semantic/vector retrieval for RAG scenarios. See: https://learn.microsoft.com/azure/search/search-howto-indexing-azure-blob-storage and https://learn.microsoft.com/azure/search/overview

Question 15

Question#15Topic1

DRAG DROP -
You have a Microsoft Foundry project that contains a customer support agent grounded in internal documentation.
After a recent update, users report the following issues:
Some answers are unsupported by retrieved documents.
A small number of responses are flagged for policy violations.
You need to evaluate each issue.
Which observability signals should you use for each issue? To answer, drag the appropriate observability signals to the correct issues. Each observability signal may be used once, more than once, or not at all. You may need to drag the spit bar between panes or scroll to view content.
NOTE: Each correct selection is worth one point.
Question illustration

Show answer

Answer

AC

Downloads and personal use

  • Purchase this exam question set separately with 1, 3, 6 or 12 months of download access.
  • After payment confirmation, your library shows the download link and exact expiry time.
  • Download again during your term. Purchase a new term after expiry.
  • PDFs are licensed for personal study only and must not be resold or shared publicly.
  • Files already saved to your device are not remotely deleted when access expires.
How to choose your certification