IT training across Europe - tecnovy makes you future-ready.

Switch to English
E-Learning

tecnovy AI Suite

Microsoft Certified: Azure AI Apps and Agents Developer Associate (AI-103)

At the base sits Microsoft Foundry with its models, agents and deployments. The Foundry Tools build on it, among them Azure Content Understanding for images and documents and Azure Translator for text. Azure AI Search adds semantic, hybrid and vector search for grounding. Microsoft's AI-103 exam spans this stack. In the training you build RAG applications and agents on it in Python and secure them with managed identity and guardrails.
Attendance certificate4.8/5 on ProvenExpert

What this module delivers.

For Python developers on Azure: in the tecnovy AI-103 training you build RAG applications and multi-agent solutions in Microsoft Foundry and prepare for the Microsoft exam. Afterwards your team plans managed identity, guardrails and monitoring in from the start.

How the training runs

Method
Concept blocks and hands-on exercises in Microsoft Foundry with Python
Basis
Microsoft AI-103 study guide, as of 16 April 2026
Outcome
AI-103 exam with Microsoft, fee separate, plus tecnovy certificate of participation

Dates & booking

Choose a date that fits

No public dates are scheduled yet.

New dates are published regularly. Join the waitlist or plan an in-house course for your team.

Request in-house training

Fit

Who this module is designed for

Typical roles

  • You develop software in Python and are expected to build AI applications and agents on Azure.
  • You had planned AI-102 and need Microsoft's current path now that it has been retired.
  • You deliver AI solutions together with architects, data scientists and DevOps engineers.

Prerequisites

No prerequisites

You can start right away. What you need: experience developing apps in Python, familiarity with generative AI and Azure services. Helpful: Azure AI Fundamentals (AI-901) as an introduction to Microsoft Foundry.

Consider instead LLM Engineering For anyone who wants to build LLM applications in Python without tying them to Azure, and without an exam.

Curriculum

AI-103 Course in Detail

The tecnovy training follows the five exam domains in Microsoft's AI-103 study guide (as of 16 April 2026), with Microsoft's weighting in each title. Not covered as topics of their own are, among others, CI/CD integration, quota and cost management, video generation and analysis, image editing, sentiment detection, custom speech models and prompt injection through text in images.

01Plan and manage an Azure AI solution (25–30 %)

This part settles which services a solution stands on and how you secure it.

  • Choosing models and Foundry services to fit the task
  • Security with managed identity, private networking and roles
  • Safety filters, guardrails and content moderation
02Implement generative AI and agentic solutions (30–35 %)

The largest exam domain: this is where applications and agents take shape in Microsoft Foundry.

  • RAG with retrieval and indexing
  • Agents with tools, memory and knowledge sources
  • Orchestrating multiple agents
  • Evaluating and monitoring agents
03Implement computer vision solutions (10–15 %)

Here your solutions work with images instead of text.

  • Analysing image content with multimodal models
  • Generating images with generative models
04Implement text analysis solutions (10–15 %)

This part connects written and spoken language to your agents.

  • Translating text
  • Adapting language models to domain tasks
  • Speech as an input and output channel for agents
05Implement information extraction solutions (10–15 %)

Finally you extract content from documents in a form agents and RAG can work with.

  • Multimodal pipelines with OCR, layout analysis and field extraction
  • Structured output with Azure Content Understanding
Official syllabus(external link)

Outcome

What you will be able to do afterwards

  1. 01

    You select the right model and the right Foundry service for a task.

  2. 02

    You build RAG applications in Microsoft Foundry, from indexing to retrieval.

  3. 03

    You develop agents that use tools, memory and knowledge sources.

  4. 04

    You orchestrate multiple agents and evaluate and monitor their behaviour.

  5. 05

    You analyse images with multimodal models and generate new ones from prompts.

  6. 06

    You translate text, adapt language models to domain tasks and use speech as a channel for agents.

  7. 07

    You extract fields from documents with OCR and layout analysis and deliver structured output.

  8. 08

    You secure AI solutions with managed identity, private networking, roles and content filters.

Microsoft Certified: Azure AI Apps and Agents Developer Associate

Microsoft awards the Associate-level certification for a passed AI-103 exam. It expires annually and is renewed with a free online assessment on Microsoft Learn, open in the six months before it expires.

Certification terms learn.microsoft.com ↗

Examination

Microsoft exam AI-103

700Passing score (scale 1 to 1,000)

Time allowed
120 min
Fee in Germany (as of November 2026)
126 EUR
Delivery
Pearson VUE

Microsoft offers AI-103 in ten languages, German among them (as of November 2026). During the exam you may look things up on Microsoft Learn, and the clock keeps running.

Official examination rules learn.microsoft.com ↗

Offer scope

What the course price does not cover

Not included

  • Microsoft exam feeMicrosoft charges EUR 126 plus applicable taxes per attempt in Germany and the local price elsewhere (as of November 2026).

Why tecnovy

What you get on top with us

01

No Slideshow, Hands-On!

Promised: no PowerPoint marathon. We work in groups, tie theory to practice, and you get real project examples from our experienced trainers plus the exchange with like-minded people.

02

Certificate Showroom

Get your certificate of participation and, if you have one, add your exam certificate from E-Learning. Fully automated, beautifully designed. Just for you, only at tecnovy.

03

Flexible Date Change

If you are not able to attend the course, you can rebook your training free of charge up to one week before the start of the training.

04

Attend Twice, Pay Once

You are welcome to visit the training course online again within a year as a refresher or exam preparation.

05

Learn from Experts

We always guarantee you the use of didactically and methodically first-class qualified trainers who draw their knowledge from training experience as well as professional practical and project experience.

FAQs

Frequently asked questions

01Can I still take AI-102 instead of AI-103?
No, Microsoft retired the AI-102 exam and the Azure AI Engineer Associate certification on 30 June 2026 and names AI-103 with Azure AI Apps and Agents Developer Associate as the replacement. If you already hold Azure AI Engineer Associate, it stays valid until it expires, but it can no longer be renewed.
02Can I take the AI-103 exam in German?
Yes, Microsoft offers AI-103 in ten languages, German and English among them (as of November 2026). According to the study guide, Microsoft updates translated versions about eight weeks after the English one. If the exam is not offered in your preferred language and you are not proficient in the exam language, you can request 30 extra minutes before scheduling; Microsoft asks for a confirmation from an instructor or employer.
03How does the AI-103 exam work?
Microsoft delivers AI-103 through Pearson VUE, online proctored or at a test centre and separately from the tecnovy training. You have 120 minutes, and Microsoft does not name the question types in advance but shows them in its exam sandbox. You may look things up on Microsoft Learn during the exam, with no extra time added for it.
04What score do I need to pass AI-103?
You need at least 700 on a scale of 1 to 1,000 to pass AI-103. Because Microsoft scales the score, that does not necessarily equal 70 % of the points. Wrong answers cost nothing, and the score report shows your performance per skill area as a bar.
05What happens if I do not pass the AI-103 exam?
You can retake AI-103 no sooner than 24 hours after your first attempt, and after that 14 days must pass between attempts. Microsoft allows at most five attempts in twelve months from the first, and each retake costs the exam fee, which is not part of the tecnovy course price.
06How long is the Azure AI Apps and Agents Developer Associate certification valid?
One year; before expiry you renew it free of charge with an online assessment on Microsoft Learn. It is open in the six months before expiry, unproctored and open book, and you can retake it as often as you need before expiry. If you pass, Microsoft extends the certification by one year from its current expiry date.
07What do I need for the exercises in the AI-103 training?
The exercises in the tecnovy AI-103 training run in Microsoft Foundry with Python, so they need access to an Azure subscription in which Microsoft Foundry can be used.
08Do I need AI-901 before taking AI-103?
No, Microsoft names no prior exam for AI-103. Microsoft aims Azure AI Fundamentals (AI-901) at beginners who want to build AI apps and agents with Microsoft Foundry, and it is a good step before the tecnovy AI-103 training if Foundry is new to you.
09How does the AI-103 training differ from LLM Engineering?
LLM Engineering is tecnovy's vendor-neutral course with no exam: you build LLM applications in Python through model APIs, with prompt design, JSON schemas, tool use and tests. The tecnovy AI-103 training works in Microsoft Foundry on Azure instead and prepares you for the Microsoft exam.

What does your training at tecnovy look like?

AI-103Certified: Azure AI Apps and Agents Developer Associate

No dates yet

We will let you know as soon as the next date is scheduled.

Feedback Form
What should we improve?

Tell us what we can do better next time.

Success
Error

© Copyright 2026, tecnovy GmbH, All Rights Reserved