EnglishDeutschFrançaisEspañolPortuguês

Microsoft · AI-103 · Associate

Developing AI Apps and Agents on Azure (AI-103) — Practice Questions and Mock Exam

Practice real AI-103 questions, never dumps. Alex explains every answer, and your readiness score tells you when you're ready to pass.

50Questions
120minTime Limit
700/ 1000Pass Score

Checked against Microsoft · July 2026Current exam version

About the exam

Exam AI-103, Developing AI Apps and Agents on Azure, leads to the Microsoft Certified: Azure AI Apps and Agents Developer Associate certification. It is the successor to AI-102, which retires on 30 June 2026, and shifts the focus from wiring up pre-built Azure AI services to building generative AI applications and multi-agent solutions on Microsoft Foundry.

The exam targets Azure AI engineers who design, build, deploy, and operate AI apps and agents using Foundry, Azure OpenAI models, Azure AI Search, Azure AI Content Understanding, and the Azure AI Language, Vision, and Speech capabilities. You are expected to develop in Python and to understand generative AI patterns such as retrieval-augmented generation (RAG), tool calling, agent orchestration, and responsible AI.

What's on the exam

Expect roughly 40 to 60 questions in about 120 minutes. Item types include single-answer multiple choice, multiple-response (select all that apply), and drag-and-drop ordering or mapping, with scenario-based stems that ask you to apply two or more concepts together. The score is reported on a 1 to 1000 scale and 700 is required to pass. AI-103 is a beta/early exam built on Microsoft Foundry, so questions emphasise generally available features and only cover preview features that are commonly used.

Plan and manage an Azure AI solution25–30%

Choose appropriate Microsoft Foundry services and models, set up and deploy AI solutions, manage/monitor/secure AI systems, and implement responsible AI across generative and agentic systems.

Implement generative AI and agentic solutions30–35%

Build generative apps with Foundry (RAG, tool-augmented flows), build agents (roles, function-calling, memory, multi-agent orchestration), and optimize and operationalize generative AI systems.

Implement computer vision solutions10–15%

Image and video generation and editing, multimodal understanding and captioning, video analysis, and responsible AI for multimodal content.

Implement text analysis solutions10–15%

Language-model text analysis (entities, sentiment, translation, custom outputs) and speech solutions (speech-to-text, text-to-speech, speech as an agent modality).

Implement information extraction solutions10–15%

Build retrieval and grounding pipelines (semantic, hybrid, and vector search; RAG ingestion) and extract content from documents with Content Understanding.

SourceMicrosoft study guide

What to expect

Multiple Choice60%
Multiple Response25%
Drag & Drop15%

Try it now

Practice real AI-103 questions

Five sample questions from our Developing AI Apps and Agents on Azure bank. Answer one — Alex, your AI tutor, explains the why. Real prep, never dumps.

Where candidates struggle

The most common trap is answering from older AI-102 knowledge. Multi-agent orchestration in the new Foundry Agent Service uses workflows, the Microsoft Agent Framework, and the agent-to-agent (A2A) tool — the classic Connected Agents tool is deprecated and is not part of the new service. Other frequent mistakes: reaching for fine-tuning when retrieval (RAG with Azure AI Search hybrid or vector search) is the grounded answer; putting API keys in config instead of using managed identity and keyless credentials; confusing Azure AI Document Intelligence with Azure AI Content Understanding for multimodal extraction; and forgetting responsible-AI instrumentation (content filters, safety evaluators, trace logging and provenance) that the exam explicitly tests.

  1. 01
    Connected Agents vs Foundry workflows — Classic Connected Agents is deprecated and absent from the new Foundry Agent Service; orchestrate multiple agents with Foundry workflows, the Microsoft Agent Framework, or the A2A tool.
  2. 02
    RAG before fine-tuning — Ground responses with retrieval (Azure AI Search hybrid/vector search) rather than fine-tuning when the goal is adding domain knowledge or reducing fabrications.
  3. 03
    Keyless, managed-identity auth — Secure Foundry resources with managed identity, private networking, and keyless credentials instead of storing API keys.
  4. 04
    Content Understanding vs Document Intelligence — Use Azure AI Content Understanding for multimodal extraction and grounded RAG inputs; do not assume Document Intelligence covers video/audio.
  5. 05
    Responsible AI is tested — Know content filters, safety evaluators, risk detection, trace logging, and provenance metadata as first-class exam topics, not afterthoughts.
  6. 06
    GA over preview — Answer for generally available behaviour; preview features appear only when commonly used.

Exam logistics

The exam is delivered through Pearson VUE at a test center or as an online-proctored exam. A passing score is 700 on a 1 to 1000 scale. Microsoft associate certifications expire after one year and are renewed for free by passing a short online renewal assessment on Microsoft Learn. After a failed first attempt you must wait 24 hours before retaking; longer waits apply to subsequent attempts, with a limit of five attempts in a 12-month period.

Exam fee$165 USD
DeliveryPearson VUE (test center or online proctored)
Retake policy24-hour wait after a failed first attempt; escalating waits after; max 5 attempts per 12 months
Validity1 year
Career outcomesAzure AI Engineer, AI Application Developer, Generative AI Engineer, and AI Agent Developer roles building production AI apps and agents on Azure.
RenewalRenew for free each year by passing the online renewal assessment on Microsoft Learn before the certification expires.
Study time~45 hours
Official guideView on vendor site

SourceMicrosoft study guide

Before you book the exam

Would you pass AI-103 today?

Take the free readiness check. Answer real AI-103 questions and get your readiness score across every domain.

Take the free readiness check20 questions · free

Reach 80% readiness by exam day. Pass, or your money back.

Ready to commit? Own AI-103 for $29.99 →