‹ All AI-103 questions

AI-103 Practice Question 11: Least Privilege Agent Role

Microsoft Azure AI Apps and Agents Developer Associate (AI-103) · Test 2 · question 1 of 10

Plan and manage an Azure AI solutionmedium

An order-management microservice needs to call a published prompt agent's endpoint in a Microsoft Foundry project. Security review requires that the service principal be able to do nothing else: it must not create, update or delete agents, must not read project or resource configuration, and must not be able to assign roles. The platform team wants a built-in role rather than a custom one, scoped as narrowly as the role supports.

Which role assignment meets the requirement?

Select one answer
Show answer and explanation

Answer:

  • B. Foundry Agent Consumer, assigned at the project scope with the Azure CLI

Foundry Agent Consumer is the least-privilege role in the Foundry built-in role table: it is the only role whose sole permission is *interact with agent endpoints*. It cannot create projects or accounts, cannot perform data actions, cannot complete role assignments, and does not even carry reader access. The CLI detail matters too; the Azure portal currently supports assigning Foundry Agent Consumer only at the account scope, so assigning it at project (or individual agent) scope has to be done with az role assignment create.

- A is wrong because Foundry User adds reader access to the project and resource *and* the data actions used to build and develop agents. It is the least-privilege role for a developer, not for a caller that only invokes an endpoint. - C is wrong because Foundry Project Manager is far broader: it can build in the project, publish agents, and conditionally assign the Foundry User role to other principals. - D is wrong because Microsoft explicitly says not to assign roles beginning with *Cognitive Services* for Foundry scenarios; those roles target Azure AI services resources directly and don't map to Foundry project permissions.

Reference: Role-based access control for Microsoft Foundry

Practice Test 2 ›

Study guides for AI-103

AI engineer roadmap 2026: skills, certs and the orderAI engineer roadmap for 2026: skills to learn in order, AI engineer vs ML engineer, which certifications fit each stage, and what to skip.
AI-200 exam guide: Azure AI Cloud Developer AssociateAI-200 replaced AZ-204: what the Azure AI Cloud Developer exam tests, how it differs from AI-103, price in USD and INR, format and how to prepare.
How AI Is Changing Software Jobs: Where to PrepareHow AI is changing software jobs: what history shows, the evidence on junior developers, what Klarna learned, new AI roles and five domains to prepare for.
AI-901 exam guide: Azure AI Fundamentals after AI-900AI-901 replaced AI-900: learn what changed, how much Python and Microsoft Foundry you need, exam costs in India, and how to prepare.
Best AI certifications 2026: AWS, Google, Microsoft, ClaudeThe best AI certifications in 2026 from AWS, Google, Microsoft, Claude and Databricks, by level, with price, status and which one to take first.
Microsoft AI certification path 2026: which exam firstMicrosoft AI certification path for 2026 - AI-901, AB-730, AI-103, AI-200, AI-300, AB-100, AI-500 and GH-300 by role, and which exam to take first.
AI-103 Certification Guide: What Changed From AI-102The AI-103 certification replaced AI-102 in 2026. Exam format, cost, the five skill domains, what changed and how to prepare, with free practice questions.
What Is RAG? How Retrieval-Augmented Generation WorksWhat RAG is and how it works: chunking, embeddings, vector search, hybrid search, reranking, GraphRAG and agentic RAG on AWS, Google and Azure.
Prompt engineering vs RAG vs fine-tuningWhen to use prompt engineering, retrieval-augmented generation, fine-tuning or continued pre-training, compared on cost, freshness, hallucination and privacy.