Build generative AI applications and intelligent agents on Azure with Microsoft Foundry, RAG, MCP tools, and multi-agent orchestration. 4-day official course aligned to Exam AI-103, replacing AI-102.

👥 2183 Enrolled ⏱️ 4 Days 💼 Intermediate Level ⭐ 5 ( 173 ) Reviews

500+Courses

10+ YrsExperience

95K+Global Learners

Live Online (Public Batch)

Instructor-led group class, fixed schedule

USD 2295

Private Group

Train your whole team, on your dates

Custom Quote

For Teams

Proceed to Buy Request Info

📄 Download Course PDF

100% Satisfaction Guarantee · Guaranteed to Run · Secure Payment

Course Overview

Microsoft has rebuilt its Azure AI certification around what developers are actually being asked to deliver: applications that reason, agents that act, and systems that stay grounded in company data. AI-103T00 is the course for that work, and it replaces AI-102 as the path to Microsoft's associate-level Azure AI credential.

The four days move through the full development picture. You start in Microsoft Foundry, exploring the model catalog, selecting models against benchmarks, deploying to endpoints, and evaluating performance before anything reaches production. From there you build generative AI chat applications with the Responses and ChatCompletions APIs, extend them with tools including code interpreter, web search, file search, and custom functions, then optimize output through prompt engineering, RAG grounding, and fine-tuning.

The agent content is the largest part of the course and the reason to take it. You build and deploy agents in Foundry and Visual Studio Code, integrate custom tools, connect MCP servers and clients, ground agents in enterprise knowledge with Foundry IQ, publish agents to Microsoft Teams, and create agent-driven workflows with Power Fx. Then it goes further into orchestration: multi-agent solutions with Microsoft Agent Framework using concurrent, sequential, group chat, handoff, and Magentic patterns, plus remote agent discovery through A2A.

The last two sections cover language, speech, and vision. Text analysis and PII extraction, speech transcription and synthesis, Voice Live agents, translation, then vision-enabled chat apps, image and video generation, Content Understanding for multimodal analysis, Document Intelligence, and knowledge mining with Azure AI Search.

Responsible AI runs throughout, with a dedicated section on mapping, measuring, and mitigating potential harms.

Mode of Training

🏫 Classroom 💻 Live Online 🧪 Blended 👨‍👩‍👧‍👦 Private Group

Upcoming Schedules

Start Date	Time	Duration	Mode	Price
Sep 22, 2026	9:00 am - 5:00 pm	4 Days	online	$2295	GTR
Oct 06, 2026	9:00 am - 5:00 pm	4 Days	online	$2295	GTR
Oct 20, 2026	9:00 am - 5:00 pm	4 Days	online	$2295	GTR
Nov 03, 2026	9:00 am - 5:00 pm	4 Days	online	$2295	GTR

+ View more schedules

What you will learn

Develop generative AI applications using Microsoft Foundry and Azure AI services
Build, deploy, and manage AI agents using Foundry Agent Service and agent frameworks
Implement Retrieval-Augmented Generation for knowledge-based AI solutions
Integrate custom tools, APIs, and enterprise data into AI agents
Design natural language, speech, and multimodal AI solutions
Apply responsible AI practices and optimize model performance

Who Should Attend This Course?

AI engineers and software developers building AI applications on Azure
Cloud developers moving into generative AI and agent development
Data scientists who need to ship applications rather than notebooks
Automation architects designing agent-driven workflows
Anyone who was working toward AI-102 and needs the current path

Prerequisites

Required:

Programming experience, preferably Python
A basic understanding of APIs and SDKs

Recommended:

Familiarity with Azure services and the Azure portal
An understanding of AI and ML concepts and generative AI basics
Experience working with REST APIs and cloud-based applications

You do not need machine learning depth. What the course assumes is that you can write code and work comfortably with SDKs and APIs.

📞 Talk to a Learning Advisor

Exam and Certification

This course prepares you for Exam AI-103: Developing AI Apps and Agents on Azure, leading to the Microsoft Certified: Azure AI Apps and Agents Developer Associate credential.

Exam duration: 120 minutes
Passing score: 700 out of 1000
Format: multiple choice, case studies, and lab-based questions

The exam is booked and paid for separately from the course.

Important: the AI-102 transition

AI-103 replaces AI-102. Exam AI-102 and the Microsoft Certified: Azure AI Engineer Associate certification retired on 30 June 2026, along with the renewal assessment for that credential.

What this means in practice:

If you hold Azure AI Engineer Associate, it stays on your transcript until its printed expiration date, but there is no renewal path. Once it lapses, the only way to hold a current Azure AI developer credential is AI-103.
If you were mid-study for AI-102, registrations are closed. The overlap is real, since vision, language, and knowledge-mining skills carry over, but the balance has moved sharply toward agents and Microsoft Foundry.
If you are starting fresh, there is no decision to make. AI-103 is the path.

Study material published before spring 2026 is aimed at the retired exam. Anything referencing Azure AI Studio, Prompt Flow, or Semantic Kernel as the primary tooling is out of date; the current platform is Microsoft Foundry with the Foundry Agent Service and Microsoft Agent Framework.

📘 AI-103T00: Develop AI Apps and Agents on Azure Outline

Plan and prepare. What AI is, Microsoft Foundry and Foundry Tools, developer tools and SDKs, and responsible AI. Exercise: prepare for an AI development project.

Select, deploy, and evaluate models. Explore the model catalog, select models using benchmarks, deploy to endpoints, and evaluate performance. Exercise: select, deploy, and evaluate models.

Build a generative AI chat app. Work in the model playground, choose an endpoint and SDK, and generate responses with the Responses API and the ChatCompletions API. Exercise: create a generative AI chat app.

Use tools. The code_interpreter, web_search, file_search, and functions tools. Exercise: create a chat app that uses tools.

Optimize performance. Prompt engineering, grounding with RAG, fine-tuning for consistent behaviour, and comparing or combining optimization strategies. Exercise: optimize generative AI model performance.

Responsible AI. Plan a responsible solution, then map, measure, mitigate, and manage potential harms. Exercise: apply guardrails to prevent harmful content.

Foundry Agent Service and Visual Studio Code. Understand agents and the Agent Service, explore development approaches, build your first agent, configure and manage agents in VS Code, extend capabilities with tools, then test, deploy, and integrate. Exercise: build and deploy an AI agent.

Custom tools. Why and when to use them, implementation options, and integration. Exercise: build an agent with custom tools.

MCP tools. MCP tool discovery, integrating tools through an MCP server and client, and using Azure AI agents with MCP servers. Exercise: connect MCP tools to Azure AI Agents.

Foundry IQ. RAG for agents, configuring data sources for knowledge bases, and configuring retrieval. Exercise: integrate an AI agent with Foundry IQ.

Microsoft 365 integration. Agent publishing options, publishing to Teams, the Microsoft 365 Agents Toolkit, and accessing Microsoft 365 data with Work IQ. Exercise: publish a Foundry agent to Teams.

Agent-driven workflows. Workflow patterns, creating workflows in Foundry, adding agents, applying Power Fx, maintenance, and using workflows in code. Exercise: create an agent-driven workflow.

Microsoft Agent Framework. Create an Azure AI agent and add tools to it. Exercise: develop an Azure AI agent.

Multi-agent orchestration. Concurrent, sequential, group chat, handoff, and Magentic orchestration patterns. Exercise: develop a multi-agent solution.

A2A. Define an A2A agent, implement an agent executor, host an A2A server, and connect to it. Exercise: connect to remote Azure AI Agents.

Text analysis. Azure Language in Foundry Tools, language detection, entity extraction, and PII extraction. Exercises: analyze text, and develop a text analysis agent using the Language MCP server.

Speech. Choose a speech-capable model, transcribe and synthesize speech, use the Speech to Text and Text to Speech APIs, configure audio formats and voices, and work with Speech Synthesis Markup Language. Exercises: use speech-capable AI models, create a speech-enabled app, and use Azure Speech in an agent through the Speech MCP server.

Voice Live agents. The Azure Voice Live API and client library. Exercise: develop a Voice Live agent.

Translation. Translation in Microsoft Foundry for both text and speech. Exercise: translate text and speech.

Vision-enabled applications. Use a vision-capable model and build a vision-based chat app. Exercise: develop a vision-enabled chat app.

Image and video generation. Image-generation models and client applications, then deploying a video-generating model and generating video from a prompt. Exercises: generate images with AI, and generate video.

Content Understanding. Analyze images, create analyzers, use the Content Understanding API, and build a client application. Exercises: analyze images, extract information from multimodal content, and develop a client application.

Document Intelligence. The Document Intelligence Studio, prebuilt models, and training custom models. Exercise: analyze documents.

Knowledge mining with Azure AI Search. Extract data with an indexer, enrich it with AI skills, search an index, and persist data in a knowledge store. Exercise: create a knowledge mining solution.

❓ Frequently Asked Questions

It retired on 30 June 2026, along with the Azure AI Engineer Associate certification and its renewal assessment. AI-103 is the replacement, and it leads to a new credential: Azure AI Apps and Agents Developer Associate. The shift is not just a rename. AI-102 focused on implementing Azure AI services such as vision, speech, and language. AI-103 is built around generative AI applications, agents, RAG, and Microsoft Foundry.

It remains valid until its expiration date, but it cannot be renewed. When it lapses, AI-103 is how you hold a current Azure AI developer credential. The good news is that a meaningful share of your existing knowledge carries over, particularly around vision, language, and Azure AI Search.

Roughly half. Section 2 is the largest in the syllabus, covering agent development in Foundry and VS Code, custom tools, MCP integration, knowledge grounding through Foundry IQ, Teams publishing, workflows with Power Fx, multi-agent orchestration with Microsoft Agent Framework, and remote agent connection through A2A. If your interest is agents specifically, this is the Microsoft course that goes deepest.

It is Microsoft's platform for building, deploying, and managing AI applications and agents on Azure, and it is the environment this course works in throughout. It includes the model catalog, evaluation tooling, the Foundry Agent Service, and Foundry IQ for knowledge grounding.

Model Context Protocol is the standard for connecting agents to external tools and data sources, and the course covers building MCP servers and clients as well as using the prebuilt Azure Language and Speech MCP servers. A2A covers agent-to-agent connection, letting you define, host, and connect to remote agents. Both are current, and both are rare in official courseware.

No. AI-200 covers the cloud application engineering underneath AI workloads: containers, serverless, vector databases, messaging, and observability. AI-103 covers building the AI applications and agents themselves in Microsoft Foundry. Different exams, different certifications. Some developers eventually take both.

Yes, extensively. Nearly every topic ends with a guided exercise, covering model deployment and evaluation, chat apps, tool use, guardrails, agent building and publishing, MCP connection, multi-agent orchestration, speech and vision applications, document analysis, and knowledge mining.

Still have questions?

Reach out to our learning advisors for personalized guidance on choosing the right course, group training, or enterprise packages.

📞 Talk to an Advisor

What You Get with Microtek Learning

Instructor-Led Excellence

✓ Certified Instructor-led Training
✓ Top Industry Trainers
✓ Official Student Handbooks

Measurable Learning Outcomes

✓ Pre- & Post-Training Assessments
✓ Practice Tests
✓ Exam-Oriented Curriculum

Real-World Skill Building

✓ Hands-on Activities & Scenarios
✓ Interactive Online Courses
✓ Peer Collaboration (Not in self-paced)

Full Support & Perks

✓ Exam Scheduling Support ^*
✓ Learn & Earn Program ^*
✓ Support from Certified Experts
✓ Gov. & Private Pricing ^*

Our Clients

For over 10 years, Microtek Learning has helped organizations, leaders, students and professionals to reach their maximum potential. We have led the path by addressing their challenges and advancing their performances.