Skip to content
EDWartens UK

Free course · AI and machine learning

Azure AI Apps and Agents Developer (AI-103) Exam Preparation

Preparation for Microsoft's AI-103 exam, built on the skills measured as of 16 April 2026: planning, securing and monitoring Microsoft Foundry solutions, generative apps and RAG, agents with tools, MCP and multi-agent workflows, vision, text, speech and information extraction with Content Understanding and Azure AI Search. Preparation for the exam, not the Microsoft certification itself.

See the modules

Free to learn. Verifiable certificate £19 when you pass the final exam (optional, VAT included).

Level
Intermediate
Modules
15
Video
19 hours
Price
Free

Outcome

What you will be able to do

Name the AI-103 skill areas and their weights and plan your study against them; choose models, deployment types and Foundry services for a scenario; secure a Foundry solution with managed identities, roles and private endpoints; build a chat app and agents with tools, MCP servers, knowledge and approvals; orchestrate several agents with Microsoft Agent Framework; evaluate, trace and monitor them; use vision, text, speech and Content Understanding; build a retrieval pipeline with Azure AI Search; and sit Microsoft's exam with a method for scenario questions.

  • Map your study to the AI-103 skills measured as of 16 April 2026 and their weights
  • Choose a model, a deployment type and the Foundry services for a stated scenario
  • Secure a Foundry solution with managed identities, least-privilege roles and private endpoints
  • Build a Python chat app and agents with function, OpenAPI and MCP tools behind human approval
  • Orchestrate several agents with Microsoft Agent Framework and Foundry workflows
  • Evaluate, trace and monitor generative apps and agents, and configure guardrails
  • Use Azure Language, Translator, Speech, Voice Live and multimodal vision for stated tasks
  • Extract content with Content Understanding and build hybrid retrieval with Azure AI Search

Software

An Azure subscription: an Azure free account, or Azure for Students where you qualify. The Microsoft Foundry portal in the browser, Python 3 with the azure-ai-projects, azure-identity and agent-framework packages, the Azure CLI for sign-in, Visual Studio Code with the Microsoft Foundry extension, and Azure AI Search on its free tier, all free to install. Delete resources you no longer use, because model calls, search and some Foundry features are billed by use.

Hardware

A computer with a browser and Python; a microphone for the speech module.

Syllabus

15 modules

Each module has video lessons, notes and a short quiz. The final exam closes the course.

  1. 1The AI-103 exam, the retired AI-102, and planning an AI solution on Azure1 lesson
  2. 2Choosing, deploying and evaluating Foundry models1 lesson
  3. 3Infrastructure, security and CI/CD for Foundry projects2 lessons
  4. 4Building a generative AI chat app with the Foundry SDK1 lessonLab
  5. 5Tools, function calling and optimising generative AI performance2 lessonsLab
  6. 6Responsible AI, evaluation and monitoring in production3 lessonsLab
  7. 7Building agents with Foundry Agent Service, VS Code and custom tools2 lessons
  8. 8Knowledge and tools for agents: MCP servers, Foundry IQ and Microsoft 3653 lessonsLab
  9. 9Agent workflows and multi-agent orchestration with Microsoft Agent Framework3 lessons
  10. 10Text analysis and translation with language models and Azure Language3 lessonsLab
  11. 11Speech solutions and speech as an agent modality4 lessons
  12. 12Computer vision: image and video generation and multimodal understanding3 lessons
  13. 13Information extraction: Content Understanding and retrieval pipelines with Azure AI Search2 lessons
  14. 14Exam technique and a full AI-103 cram review2 lessons
  15. 15Final Assessment1 lesson

How it works

How this course works

  1. Watch the video lessonsOne module at a time, at your own pace.
  2. Take the module quizA short quiz at the end of each module shows what stuck.
  3. Keep your notesWrite in My notes beside each module and ask the trainer if you are stuck.
  4. Practise in the labOptionalTry a task from the module in the EDWartens Lab, in your browser.
  5. Sit the final examPass it once you have been through the modules.
  6. Certificate, if you want oneOptionalPaid, and only after you pass. Anyone can check it online.

EDWartens Lab

Practise this in the EDWartens Lab

Practise the ideas the exam tests in the AI Workbench: prompts that set scope and format, tools within limits, approval, grounded answers and personal data removed.

Works alongside Azure AI Apps and Agents Developer (AI-103) Exam Preparation. The Lab is ai for industry practice in your browser: no install, no hardware, free to use. Sign in as a learner and it opens with your account.

Open the free lab See the Lab
AI for industry: Build AI models.

Levels to try with this course

Optional. Skip it whenever you like: it never blocks your progress or your certificate.

Why practise in a lab

Technical work is judged on what you can do: wiring, commissioning, finding a fault. Doing a task yourself teaches more than watching it a second time, and a lab lets you try it safely before you meet real equipment. It does not replace working on real hardware.

  • Practise safely, so a mistake costs nothing.
  • The lab checks your work like a site test, so you know when it is right.
  • Free, in your browser, with nothing to install.

Certificate

An optional certificate when you pass

Learning is free. Pass the final exam and you can have a certificate for £19, including VAT, with a number employers can check online. It records that you completed a free online course; it is not a regulated qualification or a CPD certificate.

  • Your name, the course, its study time and your final exam score
  • A unique certificate number and a QR code to its verification page
  • Issued by Wartens Ltd; add it to your LinkedIn profile in one click
  • Pay now or after you pass: it is issued the moment you pass the final

How the certificate works

Sample certificate for Azure AI Apps and Agents Developer (AI-103) Exam Preparation

Credits

Who made the lessons

The video lessons belong to their creators. EDWartens wrote the study plan, notes, quizzes and the final exam.

  • Microsoft Learn

    the twenty-six-episode AI-103 Develop AI apps and agents on Azure video series (planning, models, chat apps, tools, optimisation, responsible AI, agents in VS Code, custom and MCP tools, Foundry IQ, Microsoft 365, workflows, Agent Framework, Language, Speech, Voice Live, translation, vision, image and video generation, Content Understanding and Azure AI Search) and the AI-103 exam preparation session

  • John Savill's Technical Training

    the AI-103 study cram used for the full review before the exam

  • Microsoft Azure Developers

    observing and evaluating agents for quality and safety in Microsoft Foundry

  • Microsoft Mechanics

    the explainer on automating evaluations in Microsoft Foundry

  • Kamal Rathnayake - MVP

    private endpoints for Microsoft Foundry model deployments

  • cloud-monk - cloud in plain english

    a five-minute plain-English demo of Azure managed identities

Questions

About this course

Is this the Microsoft Azure AI Apps and Agents Developer Associate certification?
No. This is a free preparation course for Microsoft's AI-103 exam. The Microsoft Certified: Azure AI Apps and Agents Developer Associate certification is awarded only by Microsoft after you pass its proctored AI-103 exam, which you book and pay for with Microsoft through Pearson VUE. EDWartens is not affiliated with Microsoft, and the EDWartens certificate is a certificate of completion for this course.
Who is this AI-103 preparation course for?
Engineers and developers who write Python and want an associate-level Microsoft credential for building AI apps and agents, including those in companies worldwide that run on Microsoft. If you are new to AI on Azure, start with the Microsoft Azure AI Fundamentals (AI-901) Exam Preparation course.
What replaced AI-102?
AI-103: Developing AI Apps and Agents on Azure. Microsoft lists the Azure AI Engineer Associate certification (AI-102) and its renewal assessment as retired. AI-103 opened as a beta in April 2026 and is live; on 5 October 2026 Microsoft's certification page shows no beta label.
What does the AI-103 exam measure?
Five skill areas, as measured on 16 April 2026: plan and manage an Azure AI solution (25 to 30 percent), implement generative AI and agentic solutions (30 to 35 percent), and computer vision, text analysis and information extraction (10 to 15 percent each). You have 120 minutes and need 700 to pass. Check the study guide before you book, because Microsoft updates the outline.
Is the course free to learn?
Yes. Every module, the notes, the worked problems, the project and the final assessment are free. Only the EDWartens certificate is paid, if you want one. The Microsoft exam is booked and paid for separately with Microsoft.
Do I need an Azure subscription?
For the hands-on work, yes: an Azure free account, or Azure for Students if you are eligible. Azure AI Search has a free tier for the retrieval module. Delete resources after each module, because model calls and some Foundry features are billed by use.
How long does the course take?
About 19 hours of video, notes and practice at your own pace, of which about 14 hours is video, most of it Microsoft Learn's own AI-103 series. The optional engineering document desk project takes about 24 hours more.
What should I take next?
Go on to AI Agents and MCP for Engineers for agents connected to plant data, or to RAG and Chatbots with LangChain for deeper RAG work. The project in this course is a good portfolio piece for AI developer roles.

The Professional Module is five live days of Siemens PLC, HMI and SCADA with an instructor, then a resume session and a CPD certificate.

See the Professional Module