Develop AI Apps and Agents on Azure AI-103T00
)
Course Overview
Take your development team from using AI to building it. AI-103T00 is a four day instructor led course for software engineers who need to design, build and deploy AI infused applications and agents on Microsoft Foundry.
Delivered as dedicated group training for your organisation, the course covers generative AI application development, agents that use tools and knowledge connections, multi agent orchestration with the Microsoft Agent Framework, language and speech solutions, and multimodal work across images, video and documents. Responsible AI is built into the material rather than bolted on at the end. It also prepares your developers for the Microsoft Certified: Azure AI Apps and Agents Developer Associate certification.
AI-103 supersedes AI-102. Microsoft has retired the Azure AI Engineer Associate certification and its renewal assessment. Azure AI Apps and Agents Developer Associate, earned through Exam AI-103, is the current credential for developers building AI solutions on Azure, and this course replaces AI-102 training.
Why should you do this course?
- Move your developers from prototypes to AI solutions that are evaluated, grounded and fit to ship.
- Build agents that connect to your own tools, data and Microsoft 365 environment, rather than generic chat interfaces.
- Prepare your engineers for the Microsoft Certified: Azure AI Apps and Agents Developer Associate certification, with the exam voucher included.
- Cover model selection, evaluation and optimisation, so your team can defend the choices behind an AI feature.
- Apply responsible AI practices in the build itself, which is considerably cheaper than retrofitting them later.
What will you learn?
- Plan, prepare and secure AI solutions on Azure, and select, deploy and evaluate Microsoft Foundry models.
- Develop generative AI chat applications, including apps that call tools and external functions.
- Build AI agents with the Microsoft Foundry Agent Service and the Microsoft Agent Framework.
- Integrate custom tools and MCP tools, and connect agents to Microsoft 365 and your own knowledge sources.
- Orchestrate multi agent solutions and build agent driven workflows.
- Develop language, speech, vision and document intelligence solutions, including knowledge mining with Azure AI Search.
Who is this course for?
- Software engineers building, managing and deploying AI solutions on Microsoft Foundry.
- Development teams moving from AI experiments into applications that go to production.
- Python developers who already work with APIs and SDKs and now need the AI toolset.
- Engineers in your organisation preparing to sit the AI-103 exam.
- Teams that previously trained on AI-102 and need the current, agent focused material.
What you need to know
This is an intermediate, developer focused course, and it moves quickly. Participants should be familiar with Python and comfortable using APIs and SDKs to build applications. Existing knowledge of general AI and generative AI concepts is assumed, which is why teams often run AI-901T00 first for anyone without that grounding. Across four days your team works through the material Microsoft sets for the AI-103 certification path, building solutions hands on rather than watching demonstrations.
What's Next?
On completing the course your team will be prepared to sit Exam AI-103, the single requirement for the Microsoft Certified: Azure AI Apps and Agents Developer Associate certification. The exam runs for 120 minutes and is proctored through Pearson VUE, and an exam voucher is included with this course. View the certification details on Microsoft Learn.
Microsoft has not published a practice assessment for AI-103 yet. Practice assessments are usually released within about eight weeks of an exam becoming generally available.
Microsoft role based certifications expire unless they are renewed. Renewal is free and is done through a short online assessment on Microsoft Learn.
Skills measured
- Plan and manage an Azure AI solution
- Implement generative AI and agentic solutions
- Implement computer vision solutions
- Implement text analysis solutions
- Implement information extraction solutions
Course Structure
This course covers 30 modules across 4 topic areas:
1. Developing generative AI apps in Azure
Plan an AI solution, choose and evaluate models, then build generative AI applications that use tools and hold up to real use.
- Plan and prepare to develop AI solutions on Azure
- Select, deploy, and evaluate Microsoft Foundry models
- Develop a generative AI chat app with Microsoft Foundry
- Develop generative AI apps that use tools
- Optimize generative AI model performance with Microsoft Foundry
- Implement a responsible generative AI solution in Microsoft Foundry
2. Developing AI agents on Azure
The heart of the course: building agents with the Microsoft Foundry Agent Service and the Microsoft Agent Framework, connecting them to real tools and knowledge, then orchestrating several of them together.
- Develop AI agents with Microsoft Foundry and Visual Studio Code
- Integrate custom tools into your agent
- Integrate MCP Tools with Azure AI Agents
- Build knowledge-enhanced AI agents with Foundry IQ
- Integrate your agent with Microsoft 365
- Build agent-driven workflows using Microsoft Foundry
- Develop an AI agent with Microsoft Agent Framework
- Orchestrate a multi-agent solution using the Microsoft Agent Framework
- Discover Azure AI Agents with A2A
3. Developing natural language solutions
Text, speech and translation: analysing language, building speech capable applications, and putting agents behind both.
- Analyze text with Azure Language in Foundry Tools
- Develop a text analysis agent with the Azure Language MCP server
- Develop a speech-capable generative AI application
- Create speech-enabled apps with Azure Speech in Microsoft Foundry Tools
- Develop a speech agent with the Azure Speech MCP server
- Develop an Azure Speech Voice Live Agent in Microsoft Foundry
- Translate text and speech with Microsoft Foundry Tools
4. Extracting insights from visual data
Multimodal work: generating and analysing images and video, extracting structured data from documents, and building knowledge mining solutions.
- Develop a vision-enabled generative AI application
- Generate images with AI
- Generate videos with Microsoft Foundry
- Analyze images with Content Understanding
- Create a multimodal analysis solution with Azure Content Understanding
- Create an Azure Content Understanding client application
- Extract data with Azure Document Intelligence
- Create a knowledge mining solution with Azure AI Search
What's included
- Microsoft Official Courseware, issued digitally to every participant.
- A hands on lab environment for the practical exercises throughout the course.
- A certification exam voucher for Exam AI-103.
- Four days of instructor led training, delivered virtually or on-site at your workplace.
- A dedicated cohort for your organisation, so worked examples and questions stay relevant to what your developers are building.
Roles this course supports
Skills from this course map to the following roles in your organisation:
AI Engineer
Software Engineer or Application Developer
Solution Developer
Integration Developer
Technical Lead
Entry requirements
There are no formal entry requirements for this course, but it is written for working developers. Your team will need:
- Familiarity with Python, and experience using APIs and SDKs to build applications.
- An understanding of general AI and generative AI concepts. AI-901T00 covers this for anyone who needs it.
- Working knowledge of Azure services and how resources are provisioned and secured.
- Access to an Azure subscription at work is recommended, so what your team builds in the labs transfers back to your own environment.
Where this course fits in your team's Microsoft pathway
AI-103T00 is the developer track of Microsoft's associate level AI pathway. Teams without an AI grounding should run AI-901T00 first, and AI-300T00 covers what happens after the build: putting AI into production and keeping it healthy.
Start here
AI-901T00 Introduction to AI in Azure
This course
AI-103T00 Develop AI Apps and Agents on Azure
Pairs with
AI-300T00 Operationalize Machine Learning and Generative AI Solutions
Also relevant
AZ-400T00 Designing and Implementing Microsoft DevOps Solutions
Pricing Options
FAQs
Effectively, yes. Microsoft has retired the Azure AI Engineer Associate certification that AI-102 led to. Azure AI Apps and Agents Developer Associate, earned through Exam AI-103, is the current credential, and AI-103T00 is the instructor led course that prepares your developers for it. The material has shifted noticeably towards agents and Microsoft Foundry.
No. Microsoft courses through Upskilled Tech Academy are delivered as group training for businesses, not as on demand training for individuals. We schedule a dedicated cohort for your team, either virtually or on-site at your workplace. Get in touch and we will scope it with you.
Enough to build and debug an application unaided. The course uses Python throughout for SDK and API work, so it is not a good fit for people who are still learning the language. Teams sometimes run AI-901T00 first for developers who need the AI concepts but are strong programmers already.
Yes. An exam voucher for Exam AI-103 is included with this course. The exam runs for 120 minutes and is booked with Pearson VUE at a time that suits your team.
Not yet. Microsoft has not published one for this exam, and notes that practice assessments are usually released within about eight weeks of an exam becoming generally available. The exam sandbox, which demonstrates the question formats, is available now.
The Microsoft Official Curriculum is set by Microsoft, so exam coverage stays complete. Within that, we can adjust the emphasis across the four days, use examples drawn from your industry, and keep discussion focused on the systems your developers are actually integrating with.
Newton Godoy
Microsoft Certified Trainer
Newton is a senior Microsoft Certified Trainer with extensive experience delivering enterprise technical training across Microsoft Fabric, Azure Data Engineering, Power BI and the Azure AI ecosystem. He specialises in official Microsoft Learn instructor-led training and tailored corporate workshops, supporting enterprise teams and technical professionals across Australia and the wider APAC region.
View full profile