Training: Develop AI apps and agents on Azure (AI-103)

Ref. AI-103T00

Download PDF

Duration:

jours

Exam:

Optionnel

Level:

Intermédiaire

Funding:

Eligible

Home > Trainings > Artificial intelligence > AI Development and LLM > Azure AI Platforms > Develop AI apps and agents on Azure (AI-103)

Develop AI apps and agents on Azure Training (AI-103)

Building AI applications and agents in Azure has never been more accessible. The AI-103 training guides you through the Azure AI Foundry platform to develop, deploy and operate generative and conventional AI solutions in production environments.

In four days, you work on AI agent orchestration, GPT and Azure OpenAI model integration, Retrieval Augmented Generation (RAG) with Azure AI Search, and Azure cognitive AI services: language, vision, document intelligence, speech. The training is delivered in Geneva and Lausanne by a Microsoft Certified Trainer.

Participant Profiles

Objectives

Design and deploy AI applications in Azure AI Foundry with GPT and Azure OpenAI models
Build AI agents orchestrating multiple tools and data sources
Implement Retrieval Augmented Generation (RAG) with Azure AI Search to ground models on your data
Integrate Azure AI Language, Vision, Document Intelligence and Speech services in your applications
Secure and monitor production AI solutions with content safety and responsible AI

Prerequisites

Course Content

Module 1 : Plan and prepare to develop AI solutions on Azure

What is AI?
Microsoft Foundry
Foundry Tools
Developer tools and SDKs
Responsible AI
Module assessment

Module 2 : Select, deploy, and evaluate Microsoft Foundry models

Explore the model catalog
Select models using benchmarks
Deploy models to endpoints
Evaluate model performance

Module 3 : Develop a generative AI chat app with Microsoft Foundry

Explore with the model playground
Choose an endpoint and SDK
Generate responses with the Responses API
Generate responses with the ChatCompletions API

Module 4 : Develop generative AI apps that use tools

What are tools?
Use the code_interpreter tool
Use the web_search tool
Use the file_search tool
Use the function tool
Module assessment

Module 5 : Optimize generative AI model performance with Microsoft Foundry

Optimize model output with prompt engineering
Ground your model with Retrieval Augmented Generation
Fine-tune a model for consistent behavior
Compare and combine optimization strategies
Module assessment

Module 6 : Implement a responsible generative AI solution in Microsoft Foundry

Plan a responsible generative AI solution
Map potential harms
Measure potential harms
Mitigate potential harms
Manage a responsible generative AI solution
Module assessment

Module 7 : Develop AI agents with Microsoft Foundry and Visual Studio Code

Understand AI agents and Microsoft Foundry Agent Service
Explore development approaches
Build your first agent in Microsoft Foundry
Set up Visual Studio Code for agent development
Configure and manage agents in Visual Studio Code
Extend agent capabilities with tools
Test, deploy, and integrate agents

Module 8 : Integrate custom tools into your agent

Why use custom tools
Options for implementing custom tools
How to integrate custom tools
Module assessment

Module 9 : Integrate MCP Tools with Azure AI Agents

Understand MCP tool discovery
Integrate agent tools using an MCP server and client
Use Azure AI agents with MCP servers
Module assessment

Module 10 : Build knowledge-enhanced AI agents with Foundry IQ

Understanding RAG for agents
Explore Foundry IQ
Configure data sources for knowledge bases
Configure retrieval with Foundry IQ

Module 11 : Integrate your agent with Microsoft 365

Understand Foundry agent publishing options
Publish an agent from Foundry portal to Teams
Advanced – Use Microsoft 365 Agents Toolkit
Access Microsoft 365 data with Work IQ
Test and iterate your integrated agent

Module 12 : Build agent-driven workflows using Microsoft Foundry

Understand Workflows
Identify Workflow Patterns
Create workflows in Microsoft Foundry
Add Agents to a Workflow
Apply Power Fx in Workflows
Maintain Workflows in Microsoft Foundry
Use workflows in code
Module Assessment

Module 13 : Develop an AI agent with Microsoft Agent Framework

Understand Microsoft Agent Framework AI agents
Create an Azure AI agent with Microsoft Agent Framework
Add tools to Azure AI agent

Module 14 : Orchestrate a multi-agent solution using the Microsoft Agent Framework

Understand the Microsoft Agent Framework
Understand agent orchestration
Use concurrent orchestration
Use sequential orchestration
Use group chat orchestration
Use handoff orchestration
Use Magentic orchestration

Module 15 : Discover Azure AI Agents with A2A

Define an A2A agent
Implement an agent executor
Host an A2A server
Connect to your A2A agent
Module assessment

Module 16 : Analyze text with Azure Language in Foundry Tools

Azure Language in Microsoft Foundry Tools
Detect language
Extract entities
Extract personally identifiable information (PII)
Module assessment

Module 17 : Develop a text analysis agent with the Azure Language MCP server

Understand the Azure Language MCP server
Connect and use the Language MCP server with an agent

Module 18 : Develop a speech-capable generative AI application

Choose a speech-capable model
Transcribe speech
Synthesize speech
Module assessment

Module 19 : Create speech-enabled apps with Azure Speech in Microsoft Foundry Tools

Azure Speech in Foundry Tools
Use the Speech to Text API
Use the Text to Speech API
Configure audio format and voices
Use Speech Synthesis Markup Language
Module assessment

Module 20 : Develop a speech agent with the Azure Speech MCP server

Understand the Azure Speech MCP server
Connect and use the Speech MCP server with an agent

Module 21 : Develop an Azure Speech Voice Live Agent in Microsoft Foundry

Explore the Azure Voice Live API
Explore the AI Voice Live client library for Python
Create a Voice Live agent
Module assessment

Module 22 : Translate text and speech with Microsoft Foundry Tools

Translation in Microsoft Foundry
Translate text
Translate speech
Module assessment

Module 23 : Develop a vision-enabled generative AI application

Use a vision-capable model in the Microsoft Foundry portal
Develop a vision-based chat app
Module assessment

Module 24 : Generate images with AI

What are image-generation models?
Explore image-generation models in Microsoft Foundry portal
Create a client application that uses an image generation model
Module assessment

Module 25 : Generate videos with Microsoft Foundry

Deploy a video generating model
Generate video from a prompt
Generate video in Python
Module assessment

Module 26 : Analyze images with Content Understanding

What is Content Understanding?
Analyze images with Content Understanding
Module assessment

Module 27 : Create a multimodal analysis solution with Azure Content Understanding

What is Azure Content Understanding?
Create a Content Understanding analyzer
Use the Content Understanding API
Module assessment

Module 28 : Create an Azure Content Understanding client application

Prepare to use the AI Content Understanding API
Create a Content Understanding analyzer
Analyze content
Module assessment

Module 29 : Extract data with Azure Document Intelligence

What is Azure Document Intelligence?
Use the Document Intelligence Studio
Use prebuilt models
Train and use custom models
Module assessment

Module 30 : Create a knowledge mining solution with Azure AI Search

What is Azure AI Search?
Extract data with an indexer
Enrich extracted data with AI skills
Search an index
Persist extracted information in a knowledge store
Module assessment

Documentation

Course material included.

Exam

This course prepares you to the AI-102: Designing and Implementing a Microsoft Azure AI Solution exam.

Complementary Courses

Eligible Funding

ITTA is a partner of a continuing education fund dedicated to temporary workers. This fund can subsidize your training, provided that you are subject to the “Service Provision” collective labor agreement (CCT) and meet certain conditions, including having worked at least 88 hours in the past 12 months.

Additional Information

Azure AI Foundry: the central hub for AI development in Azure

Azure AI Foundry (formerly Azure AI Studio) is the unified environment that consolidates AI application development in the Microsoft ecosystem. The Develop AI apps and agents on Azure (AI-103) training covers project creation, model deployment, response evaluation and production deployment. You work on essential tools: prompt flow to orchestrate prompt chains, model catalog to explore GPT-4o, Phi, Mistral and open source models, and the playground for interactive testing.

Building AI agents in Azure

AI agents are at the heart of the program. You learn to design agents capable of using external tools (function calling), reasoning on multi-step plans, and interacting with structured and unstructured data sources. The program covers Azure AI Agent Service and design patterns (planner / executor, multi-agent collaboration, tool routing) that structure production agentic architectures.

Retrieval Augmented Generation (RAG) with Azure AI Search

RAG has become the standard pattern to ground generative models on enterprise data. The AI-103 training has you build a complete RAG pipeline: document ingestion, chunking, embedding generation with Azure OpenAI, vector indexing in Azure AI Search, hybrid search (vector + BM25), reranking and final generation by the LLM. You also address advanced techniques: query rewriting, multi-stage retrieval, contextual compression.

Azure AI services: language, vision, document, speech

Beyond generative AI, the training covers specialized Azure AI services: Azure AI Language (entity extraction, sentiment analysis, classification, QA), Azure AI Vision (OCR, object detection, image analysis), Azure AI Document Intelligence (structured document parsing, invoices, forms), Azure AI Speech (voice recognition, synthesis, translation). The goal is to combine these building blocks to build hybrid AI applications.

Security and responsible AI

The program integrates security and responsible AI concerns. You configure Azure AI Content Safety to filter harmful content, set up prompt and response monitoring, and apply the Microsoft Responsible AI Standard principles. Topics of prompt injection, jailbreak, data leakage and model bias are covered with associated countermeasures.

Audience and prerequisites

The Develop AI apps and agents on Azure (AI-103) training targets developers, data engineers and solution architects who build AI applications in Azure. Python or .NET development experience is required. Basic Azure knowledge (equivalent to AZ-900) and AI concepts (equivalent to AI-900) are recommended.

Microsoft Certified: Azure AI Engineer Associate exam

The AI-103 course prepares you for the AI-102: Designing and Implementing a Microsoft Azure AI Solution exam, which leads to the Microsoft Certified: Azure AI Engineer Associate certification. Note: AI-102 succeeds the previous program and AI-103 represents the evolution of the training course around agents and generative AI.

FAQ Develop AI apps and agents on Azure (AI-103)

What’s the difference between AI-103 and AI-102?

AI-102 is the Microsoft certification exam. AI-103 is the code of the training course preparing for this exam. The AI-103 content has been updated to integrate Azure AI Foundry, agents and RAG, topics now dominant in the exam program.

Do I need to know Python to take the training?

Yes, Python experience is strongly recommended. Azure AI SDKs are available in Python and .NET, but most examples use Python. Familiarity with Jupyter notebooks and REST API calls is a plus.

Does the AI-103 course include Azure OpenAI Service?

Yes, Azure OpenAI is central: GPT-4o, GPT-4 Turbo, text-embedding-3 embeddings, DALL-E. You work on deployment, fine-tuning, content filters and quotas / rate limits.

What jobs lead to the Azure AI Engineer Associate certification?

Azure AI developer, AI engineer, AI solution architect, Azure OpenAI consultant, ML engineer in Azure environment.