AI-103: Develop AI apps and agents on Azure

AI-103: Develop AI apps and agents on Azure course enables developers to design and build AI-powered applications and agents using Microsoft Foundry on Azure. Participants will learn to create generative AI solutions, develop intelligent agents, and integrate tools, APIs, and enterprise knowledge using Retrieval-Augmented Generation (RAG). The course also covers natural language processing, speech, and multimodal AI capabilities such as image and video understanding. By the end, learners will be able to develop, deploy, and manage scalable AI solutions for real-world business scenarios.

Course objectives

  • Develop generative AI applications using Microsoft Foundry and Azure AI services
  • Build, deploy, and manage AI agents using Foundry Agent Service and frameworks
  • Implement Retrieval-Augmented Generation (RAG) 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 AI model performance

Prerequisites

Required

  • Programming experience (preferably Python)
  • Basic understanding of APIs and SDKs

Recommended

  • Familiarity with Azure services and Azure portal
  • Understanding of AI/ML concepts and generative AI basics
  • Experience working with REST APIs and cloud-based applications

Target audience

  • AI Engineer
  • Software Developer
  • Data Scientist
  • Cloud Developer
  • Automation Architect

Course content:

Develop generative AI apps in Azure

Plan and prepare to develop AI solutions on Azure

  • Introduction
  • What is AI?
  • Microsoft Foundry
  • Foundry Tools
  • Developer tools and SDKs
  • Responsible AI
  • Exercise - Prepare for an AI development project


Select, deploy, and evaluate Microsoft Foundry models

  • Introduction
  • Explore the model catalog
  • Select models using benchmarks
  • Deploy models to endpoints
  • Evaluate model performance
  • Exercise - Select, deploy, and evaluate models


Develop a generative AI chat app with Microsoft Foundry

  • Introduction
  • Explore with the model playground
  • Choose an endpoint and SDK
  • Generate responses with the Responses API
  • Generate responses with the ChatCompletions API
  • Exercise - Create a generative AI chat app


Develop generative AI apps that use tools

  • Introduction
  • What are tools?
  • Use the code_interpreter tool
  • Use the web_search tool
  • Use the file_search tool
  • Use the functions tool
  • Exercise - Create a generative AI chat app that uses tools


Optimize generative AI model performance with Microsoft Foundry

  • Introduction
  • 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
  • Exercise - Optimize generative AI model performance


Implement a responsible generative AI solution in Microsoft Foundry

  • Introduction
  • Plan a responsible generative AI solution
  • Map potential harms
  • Measure potential harms
  • Mitigate potential harms
  • Manage a responsible generative AI solution
  • Exercise - Apply guardrails to prevent harmful content

Develop AI agents on Azure

Develop AI agents with Microsoft Foundry and Visual Studio Code

  • Introduction
  • 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
  • Exercise - Build and deploy an AI agent


Integrate custom tools into your agent

  • Introduction
  • Why use custom tools
  • Options for implementing custom tools
  • How to integrate custom tools
  • Exercise - Build an agent with custom tools


Integrate MCP Tools with Azure AI Agents

  • Introduction
  • Understand MCP tool discovery
  • Integrate agent tools using an MCP server and client
  • Use Azure AI agents with MCP servers
  • Exercise - Connect MCP tools to Azure AI Agents


Build knowledge-enhanced AI agents with Foundry IQ

  • Introduction
  • Understanding RAG for agents
  • Explore Foundry IQ
  • Configure data sources for knowledge bases
  • Configure retrieval with Foundry IQ
  • Exercise - Integrate an AI agent with Foundry IQ


Integrate your agent with Microsoft 365

  • Introduction
  • Understand Foundry agent publishing options
  • Publish an agent to Teams
  • Use Microsoft 365 Agents Toolkit
  • Access Microsoft 365 data with Work IQ
  • Test and iterate your integrated agent
  • Exercise - Publish a Foundry agent to Teams


Build agent-driven workflows using Microsoft Foundry

  • Introduction
  • Understand workflows
  • Identify workflow patterns
  • Create workflows in Microsoft Foundry
  • Add agents to a workflow
  • Apply Power Fx in workflows
  • Maintain workflows
  • Use workflows in code
  • Exercise - Create an agent-driven workflow


Develop an AI agent with Microsoft Agent Framework

  • Introduction
  • Understand Microsoft Agent Framework AI agents
  • Create an Azure AI agent
  • Add tools to Azure AI agent
  • Exercise - Develop an Azure AI agent


Orchestrate a multi-agent solution using Microsoft Agent Framework

  • Introduction
  • Understand the Microsoft Agent Framework
  • Understand agent orchestration
  • Use concurrent orchestration
  • Use sequential orchestration
  • Use group chat orchestration
  • Use handoff orchestration
  • Use Magentic orchestration
  • Exercise - Develop a multi-agent solution


Discover Azure AI Agents with A2A

  • Introduction
  • Define an A2A agent
  • Implement an agent executor
  • Host an A2A server
  • Connect to your A2A agent
  • Exercise - Connect to remote Azure AI Agents

Develop natural language solutions in Azure

Analyze text with Azure Language

  • Introduction
  • Azure Language in Foundry Tools
  • Detect language
  • Extract entities
  • Extract personally identifiable information (PII)
  • Exercise - Analyze text

Develop a text analysis agent

  • Introduction
  • Understand the Azure Language MCP server
  • Connect and use the Language MCP server
  • Exercise - Develop a text analysis agent

Develop a speech-capable generative AI application

  • Introduction
  • Choose a speech-capable model
  • Transcribe speech
  • Synthesize speech
  • Exercise - Use speech-capable AI models

Create speech-enabled apps

  • Introduction
  • 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
  • Exercise - Create a speech-enabled app

Develop a speech agent

  • Introduction
  • Understand the Azure Speech MCP server
  • Connect and use the Speech MCP server
  • Exercise - Use Azure Speech in an agent

Develop an Azure Speech Voice Live Agent

  • Introduction
  • Explore the Azure Voice Live API
  • Explore the AI Voice Live client library
  • Create a Voice Live agent
  • Exercise - Develop a Voice Live agent

Translate text and speech

  • Introduction
  • Translation in Microsoft Foundry
  • Translate text
  • Translate speech
  • Exercise - Translate text and speech

Extract insights from visual data on Azure

Develop a vision-enabled generative AI application

  • Introduction
  • Use a vision-capable model
  • Develop a vision-based chat app
  • Exercise - Develop a vision-enabled chat app

Generate images with AI

  • Introduction
  • What are image-generation models?
  • Explore image-generation models
  • Create a client application
  • Exercise - Generate images with AI

Generate videos with Microsoft Foundry

  • Introduction
  • Deploy a video generating model
  • Generate video from a prompt
  • Generate video in Python
  • Exercise - Generate video

Analyze images with Content Understanding

  • Introduction
  • What is Content Understanding?
  • Analyze images
  • Exercise - Analyze images

Create a multimodal analysis solution

  • Introduction
  • What is Azure Content Understanding?
  • Create a Content Understanding analyzer
  • Use the Content Understanding API
  • Exercise - Extract information from multimodal content

Create a Content Understanding client application

  • Introduction
  • Prepare to use the API
  • Create a Content Understanding analyzer
  • Analyze content
  • Exercise - Develop a client application

Extract data with Azure Document Intelligence

  • Introduction
  • What is Azure Document Intelligence?
  • Use the Document Intelligence Studio
  • Use prebuilt models
  • Train and use custom models
  • Exercise - Analyze documents

Create a knowledge mining solution with Azure AI Search

  • Introduction
  • What is Azure AI Search?
  • Extract data with an indexer
  • Enrich data with AI skills
  • Search an index
  • Persist data in a knowledge store
  • Exercise - Create a knowledge mining solution

Exam info:

This course will help you prepare for the exam Microsoft Certified: Azure AI Apps and Agents Developer Associate

Assessed on this exam

  • 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

 

 

FAQ – AI-103: Develop AI apps and agents on Azure

Hva koster kurset?
Prisen er 30 000 NOK for 5 dager. Kurset inkluderer digitalt kursmateriell og hands-on lab-øvelser.

Hvor lenge varer kurset?
Kurset går over 5 dager og gir en omfattende og praktisk innføring i utvikling av AI-applikasjoner og agenter på Azure.

Hvordan gjennomføres kurset?
Kurset kombinerer teori og praktisk utvikling i Azure-miljø. Deltakerne jobber med reelle scenarioer og bygger egne AI-applikasjoner og agenter gjennom hele kurset.

Hvem passer kurset for?
Kurset er utviklet for tekniske fagpersoner som ønsker å utvikle AI-løsninger, blant annet:

  • AI engineers
  • Software developers
  • Data scientists
  • Cloud developers
  • Automation architects

Hva lærer jeg i løpet av kurset?
Du lærer hvordan du bygger moderne AI-løsninger på Azure. Etter kurset vil du kunne:

  • Utvikle generative AI-applikasjoner med Microsoft Foundry
  • Bygge og deploye AI-agenter
  • Implementere Retrieval-Augmented Generation (RAG)
  • Integrere API-er, verktøy og bedriftsdata i AI-løsninger
  • Utvikle løsninger for tekst, tale og multimodal AI
  • Optimalisere ytelse og kvalitet i AI-modeller
  • Implementere ansvarlig og sikker bruk av AI

Er kurset praktisk rettet?
Ja. Kurset er sterkt hands-on og inkluderer en rekke lab-øvelser hvor du utvikler og tester egne AI-applikasjoner og agenter.

Hvilke temaer dekkes i kurset?
Kurset dekker blant annet:

  • Generative AI og Microsoft Foundry
  • AI-agenter og agent-orchestrering
  • RAG og knowledge-based AI
  • Natural language processing og speech
  • Computer vision og multimodal AI
  • Azure AI Search og Document Intelligence
  • Responsible AI og governance

Får jeg sertifisering etter kurset?
Kurset forbereder deg til relevante Microsoft AI-sertifiseringer, men inkluderer ikke eksamen.

Hvilke forkunnskaper anbefales?
Det kreves programmeringserfaring (helst Python) og grunnleggende forståelse av API-er. Kjennskap til Azure og AI/ML er en fordel.

Hva gjør dette kurset unikt?
Kurset gir en komplett utviklerreise fra grunnleggende AI-konsepter til avanserte agent-baserte løsninger, med fokus på moderne verktøy som Microsoft Foundry og reelle bruksområder.

Other relevant courses

4. May
5 days
Classroom Virtual Guaranteed to run
2 days
Classroom
1 days
Classroom