Start studying freeStart free

Microsoft · Associate

AI-103 exam prep

Azure AI Apps and Agents Developer

Build AI apps and agents with Microsoft Foundry: models and deployments, RAG and agents, vision, text and speech, and document extraction, with hands-on labs.

Start studying AI-103 free Sample questions
practice questions
296
chapters
26
slide decks
20
practice exams
2
case-study questions
12

The exam at a glance

Duration
120 minutes; may contain labs
Questions
Most Microsoft exams have 40 to 60
Passing score
700 on a scale of 1 to 1,000
Microsoft Learn
Open during the exam, no extra time
Retake
24 hours after the first failure, then 14 days; at most 5 in 12 months
Renewal
Yearly, free online assessment

Source: Microsoft AI-103 study guide, skills measured as of April 16, 2026

What the exam covers

Every objective in the official study guide has a chapter, a slide deck and practice questions.

  1. Plan and manage an Azure AI solution

    25–30% of the exam

    1. 1.1 Choose Foundry models and services
    2. 1.2 Set up Foundry resources and deployments
    3. 1.3 Manage, monitor, and secure AI systems
    4. 1.4 Responsible AI for generative and agentic systems

  2. Implement generative AI and agentic solutions

    30–35% of the exam

    1. 2.1 Deploy, consume, and connect models
    2. 2.2 RAG, workflows, and evaluating generative apps
    3. 2.3 Build agents with Foundry Agent Service
    4. 2.4 Multi-agent solutions, approvals, and agent monitoring
    5. 2.5 Optimize and operationalize generative AI

  3. Implement computer vision solutions

    10–15% of the exam

    1. 3.1 Generate and edit images and video
    2. 3.2 Multimodal understanding and Content Understanding
    3. 3.3 Responsible AI for multimodal content

  4. Implement text analysis solutions

    10–15% of the exam

    1. 4.1 Text analysis with language models and Foundry Tools
    2. 4.2 Speech solutions for apps and agents

  5. Implement information extraction solutions

    10–15% of the exam

    1. 5.1 Retrieval and grounding pipelines with Azure AI Search
    2. 5.2 Extract content from documents

  6. Foundations

    Background, not scored

    1. 0.1 Generative AI essentials for developers
    2. 0.2 The Azure and Python toolbox for AI apps
    3. 0.3 Microsoft Foundry at a glance

Sample questions

Three original questions from the bank, with their explanations.

Implement generative AI and agentic solutions · From chapter 2.1 Deploy, consume, and connect models

A new assistant needs tools and memory between turns.

Tidewater is starting a new support chat on an OpenAI reasoning model. The model must call a product lookup function, keep the conversation across turns without the app resending every earlier message, and carry its reasoning from one turn to the next.

Which API should the team build on?

Choose an answer

Plan and manage an Azure AI solution · From chapter 1.1 Choose Foundry models and services

A ticket router must label 40,000 short messages a day.

Each message gets one of six fixed labels. The current general LLM is accurate but adds about two seconds per message, and the finance team wants the cost per message cut. An offline test shows a smaller model reaching the same accuracy on 500 labeled messages.

Which model choice fits best?

Choose an answer

Implement computer vision solutions · From chapter 3.1 Generate and edit images and video

The banner prompt returns a paragraph.

A developer sends "Draw a banner of a tent on a beach" to Tidewater's chat deployment through the Responses API, and gets back a written description of a banner. The marketing site needs a PNG file it can show.

What should the developer do?

Choose an answer

How you will study

Learn each objective with a chapter and a slide deck, practice with a drill that brings back what you miss, then rehearse with timed exams weighted like the real one.

See how it works →

  1. 1

    Learn

    Understand it, then remember it

    Chapters with decision tables and exam traps · Slide decks with step-by-step animated diagrams · A study map of the whole exam on one page

  2. 2

    Practice

    Practice what you are about to forget

    Reviews spaced at 1, 3, 7, 14 and 30 days · Only the chapters you have finished, unless you choose more · An explanation for every option, right or wrong

  3. 3

    Pass

    Rehearse the real thing

    From a 5-question warm-up to a full-length exam · Longer Azure exams end with a complete case study · Mastery per domain against the weights the exam uses

FAQ

AI-103 FAQ

What does the AI-103 exam cover?

AI-103 (Azure AI Apps and Agents Developer) covers Plan and manage an Azure AI solution (25–30%), Implement generative AI and agentic solutions (30–35%), Implement computer vision solutions (10–15%), Implement text analysis solutions (10–15%) and Implement information extraction solutions (10–15%). 3jumps teaches each objective in 26 chapters.

How many AI-103 practice questions are there?

296 original practice questions, including 2 full practice exams. Every option has its own explanation.

How long is the AI-103 exam and what is the passing score?

Time: 120 minutes; may contain labs. Passing score: 700 on a scale of 1 to 1,000. Confirm on the official exam page before you book.

Are these real AI-103 exam questions?

No. Every question is original, written from the official objectives and checked against Microsoft's documentation. 3jumps never uses exam dumps and is not affiliated with Microsoft.

Start studying AI-103 free

Open the first chapter and let the drill take it from there.

Start studying free