Practice
Learn at your own pace. Answer questions one at a time with instant feedback and explanations.
Start practiceDeveloping AI Apps and Agents on Azure
Develop AI applications and agents on Azure by using Microsoft Foundry, generative AI, computer vision, language, speech, search, and content understanding services.
Mock exam
Simulate the real thing. Take a timed, full-length test and review your score and weak areas.
Sign up to startStudy your way: beyond Practice and Mock exam, choose adaptive, hard mode, ready review, objective coverage, or retry-your-misses — and set your own question count, timer, and pass mark.
About this exam
Exam AI-103 measures the skills required to build, manage, and deploy agents and AI solutions on Azure using Microsoft Foundry. It covers generative and agentic applications, multimodal solutions, language and speech workloads, and information extraction.
Who should take this exam
Azure AI engineers and developers who build AI applications and agents. Candidates should have experience developing applications with Python and understand general AI, generative AI, and Azure services.
Career benefits
Demonstrates practical ability to design, implement, secure, evaluate, and operate production AI applications and agent-based solutions on Azure.
How to prepare
Use the official AI-103 study guide, complete the AI-103T00 training course or equivalent Microsoft Learn paths, and practice building solutions with Microsoft Foundry and the Azure AI service portfolio.
Quick facts
Valid for1 year; renewable through Microsoft Learn
Passing score700 / 1000
FormatMultiple choice, multiple response, case studies, and scenario-based questions
Practice questions200
Objectives5
Blueprint as ofApril 16, 2026
Official pageView
What's covered
1. Plan and manage an Azure AI solution
25–30%- 1.1 Choose the appropriate Foundry services for generative AI and agents
- 1.2 Set up AI solutions in Foundry
- 1.3 Manage, monitor, and secure AI systems
- 1.4 Implement responsible AI across generative AI and agentic systems
2. Implement generative AI and agentic solutions
30–35%- 2.1 Build generative applications by using Foundry
- 2.2 Build agents by using Foundry
- 2.3 Optimize and operationalize generative AI systems
3. Implement computer vision solutions
10–15%- 3.1 Design and implement image- and video-generation solutions
- 3.2 Design and implement multimodal understanding workflows
- 3.3 Implement responsible AI for multimodal content
4. Implement text analysis solutions
10–15%- 4.1 Apply language model text analysis
- 4.2 Implement speech solutions
5. Implement information extraction solutions
10–15%- 5.1 Build retrieval and grounding pipelines
- 5.2 Extract content from documents
Frequently asked questions
Are these real exam questions?
No. These are original practice questions written to match the exam objectives, each with an explanation so you actually learn the material — not exam dumps.
How does practice mode work?
You answer questions one at a time with instant feedback and explanations. Over time the app adapts, prioritizing the objectives and questions you struggle with most.
What is a mock exam?
A timed, full-length simulation that holds feedback until the end, then shows your score, pass/fail result, and a breakdown by objective.
Can I customize how I study?
Yes. Pick the study mode that fits — adaptive practice, hard mode, ready-for-review, objective coverage, or retrying questions you've missed — and set your own question count, timer, and passing score for each session.
Do I need an account?
You can try free questions for this exam without signing in. Create a free account to save your progress, track weak objectives, and unlock the full question bank.