AzureAssociate

Microsoft Certified: Azure AI Apps and Agents Developer Associate

AI-103

Develop AI apps and agents on Azure with Microsoft Foundry: plan/manage AI solutions, implement generative AI and agentic solutions, and implement computer vision, text analysis and information extraction solutions. Successor to AI-102.

Microsoft Certified: Azure AI Engineer Associate (AI-102) is retired since 30 June 2026 — you have been redirected to the exam that replaces it.

This exam replaces Microsoft Certified: Azure AI Engineer Associate (AI-102), retired 30 June 2026.

Also on CertifyCloudx. This AI-103 question bank is the same set on our sister site certifycloudx.com, so you only need to buy it on one of the two sites.

Duration
120 min
Exam questions
—
Passing score
700 / 1000
Exam fee
Price varies by country or region
Question formats:Multiple choiceMultiple responseYes / NoYes / No statementsHot areaDrag and dropOrderingcase study
Free plan
3 free papers
Free account
Mocks locked
Pro only
Upgrade to Pro
Every paper and mock exam.
Sign in to upgrade

Start with free papers Free

You get 3 free practice papers with your plan.

Free
Mixed paper 1
Domain 1 · 25 questions
Free
Mixed paper 2
Domain 1 · 25 questions
Free
Mixed paper 3
Domain 1 · 25 questions

Domain papers 579 questions

Free
Mixed paper 1
25 questions · 60 min
Free
Mixed paper 2
25 questions · 60 min
Free
Mixed paper 3
25 questions · 60 min
Pro
Mixed paper 4
25 questions · 60 min
Pro
Mixed paper 5
25 questions · 60 min
Pro
Mixed paper 6
14 questions · 34 min
Pro
Mixed paper 7
14 questions · 34 min

Mock exams Pro

Full-length, exam-like practice tests. Available with Pro.

Mock exam 1
50 questions · 120 min
Mock exam 2
50 questions · 120 min
Mock exam 3
50 questions · 120 min

Try a sample question

All 10 sample questions →
Question 1Plan and manage an Azure AI solution

An agent calls an MCP server that reads blobs. The project's managed identity already holds Storage Blob Data Contributor on the storage account, but the tool call is rejected by the storage account. What should you correct?

  1. A.

    Assign the role to the Foundry account's system-assigned identity instead of the project's

  2. B.

    Recreate the project connection using key-based authentication so that the storage account key is passed through with each tool call instead of an Entra ID token obtained for the agent identity

  3. C.

    Assign the role to the agent identity, because the managed identity only authenticates the blueprint and the agent identity is the principal the downstream resource authorises

  4. D.

    Grant the project managed identity the Foundry User role on the storage account

Show answer

Answer: C

The agent identity, not the project managed identity, is the principal that needs RBAC on the downstream resource.

  • A. Moving the assignment between Foundry identities does not help, because neither is the principal presented to the storage account.
  • B. Reverting to keys abandons the identity model the agent tool authentication is built on and would be rejected by governance requiring keyless access.
  • C. The agent identity is documented as the principal the downstream resource authorises; the managed identity only authenticates the blueprint.
  • D. Foundry User grants access to the Foundry project and is not a data-plane role on a storage account.

What's on the exam

5 domains · 14 task statements, straight from the official exam guide (as of April 16 2026).

  1. 1.1Choose the appropriate Foundry services for generative AI and agents
    • Choose an appropriate model for each task, including large language models (LLMs), small language models, multimodal models, and Foundry Tools
    • Choose the appropriate Foundry services for generative tasks, grounding, vector search, agent workflows, or multimodal processing
    • Choose an appropriate method for retrieval and indexing
    • Choose appropriate memory, tool, and knowledge integration services for agent solutions
  2. 1.2Set up AI solutions in Foundry
    • Design Azure infrastructure for AI apps and agent-based solutions
    • Choose appropriate deployment options
    • Configure model and agent deployments
    • Integrate Foundry projects with continuous integration and continuous deployment (CI/CD) pipelines
  3. 1.3Manage, monitor, and secure AI systems
    • Manage quotas, scaling, rate limits, and cost footprints for model and agent workloads
    • Monitor model performance, drift, safety events, and grounding quality
    • Monitor data ingestion quality, search index health, and relevance performance
    • Configure security, including managed identity, private networking, keyless credentials, and role policies
  4. 1.4Implement responsible AI across generative AI and agentic systems
    • Configure safety filters, guardrails, risk detection, and content moderation
    • Apply responsible AI instrumentation, including evaluators, safety evaluations, and explanation tooling
    • Implement auditing through trace logging, provenance metadata, and approval workflows
    • Govern agent behavior with oversight modes, constraints, and tool-access controls

Outline reproduced from the vendor's public exam guide for study reference.Official guide

AI-103 practice — frequently asked questions

Are these real AI-103 exam questions?

No. Every question on CertifyAIx is original, written by us against Microsoft's publicly available AI-103 exam guide to rehearse the skills it lists. None are actual exam questions, and CertifyAIx is not affiliated with or endorsed by Microsoft.

How many AI-103 practice questions are there?

579 practice questions, including 3 full-length timed mock exams and 55 domain papers of up to 25 questions (mixed and by topic). Every question has a detailed explanation of why the right answer wins and why each distractor loses.

Is the content up to date with the current AI-103 exam guide?

The questions are written against the AI-103 exam guide dated April 16 2026, and we revise them when Microsoft updates the guide.

What question formats are covered?

The same formats the real AI-103 uses: Multiple choice, Multiple response, Yes / No, Yes / No statements, Hot area, Drag and drop, Ordering, case study. Each is rendered and graded the way the exam does it.

How long is the AI-103 exam and how many questions does it have?

According to Microsoft's published exam details: 120 minutes, passing score 700 / 1000. Our mock exams use the same time limit and question count. Always confirm current details with Microsoft before booking.

Can I practise AI-103 for free?

Yes. 3 papers are free, with up to 10 questions a day on the free plan and no card needed. Pro unlocks every paper and mock exam with no daily limit.

Does CertifyAIx guarantee that I will pass?

No practice material can guarantee a result. CertifyAIx helps you find and close your weak areas — accuracy by exam-guide domain and topic shows what to study next.