AI-103 : Develop AI applications and agents on Azure

Plan and prepare for the development of AI solutions on Azure

• Identify common AI features that you can implement in apps
• Describe Microsoft Foundry and considerations for using it.
• Describe foundry tools and considerations for using them.
• Identify the appropriate development tools and SDKs for an AI project
• Describe responsible AI considerations

Select, deploy, and evaluate Microsoft Foundry models

• Explore and filter templates in the template catalog
• Compare models using benchmark metrics for quality, security, cost, and performance
• Deploy a model to an endpoint and test it in the playground
• Evaluate model performance using manual and automated approaches
• Understand the different evaluation metrics and when to use them

Develop a generative AI conversation app with Microsoft Foundry

• Describe the process of building a generative AI conversation app with Microsoft Foundry.
• Use the conversation playground to explore patterns and generate code samples.
• Choose an endpoint, authentication method, and client SDK for your app development.
• Use the Responses API to generate AI responses in applications.
• Use the ChatCompletions API to generate AI responses in apps.

Develop generative AI applications that use tools

• Describe the functionalities of generative ARTIFICIAL INTELLIGENCE tools.
• Use the code_interpreter tool to run code and analyze data.
• Use the web_search tool to retrieve real-time information from the internet.
• Use the file_search tool to access and analyze files.
• Use the function tool to run custom code.

Optimize generative AI model performance with Microsoft Foundry

• Practice prompt engineering techniques, including system messages, learning in a few examples, and tuning model parameters to optimize the results generated.
• Understand when and how to anchor a language model using augmented recovery generation (RAG).
• Identify when fine-tuning a model improves behavioral consistency.
• Compare optimization strategies and determine when to combine them.

Implement a responsible generative AI solution in Microsoft Foundry

• Describe a global process for developing responsible AI solutions
• Identify and prioritize potential damage relevant to a generative AI solution
• Measuring the presence of damage in a generative AI solution
• Mitigating the Damage in a Generative AI Solution
• Prepare for the deployment and operation of a generative AI solution responsibly

Select, deploy, and evaluate Microsoft Foundry models

• Explore and filter templates in the template catalog
• Compare models using benchmark metrics for quality, security, cost, and performance
• Deploy a model to an endpoint and test it in the playground
• Evaluate model performance using manual and automated approaches
• Understand the different evaluation metrics and when to use them

Develop AI agents with Microsoft Foundry and Visual Studio Code

• Describe the purpose and capabilities of AI agents
• Explain the key features of the Microsoft Foundry Agent service
• Configure and install the Microsoft Foundry extension in Visual Studio Code
• Create and configure AI agents using multiple development approaches
• Extend agent functionality with tools and functions
• Test agents using built-in playgrounds
• Deploy and integrate agents into applications

Integrate custom tools with your agent

• Describe the benefits of using custom tools with your agent.
• Explore the different options for custom tools.
• Create an agent that integrates with custom tools by using the Microsoft Foundry Agent service.

Integrate MCP Tools with Azure AI Agents

• Explain the roles of the MCP server and client in discovering and calling tools.
• Encapsulate MCP tools as asynchronous functions and register them with Azure AI agents.
• Create an Azure AI agent that dynamically accesses and invokes MCP tools during runtime.

Build knowledge-enriched AI agents with Foundry IQ

• Explain how RAG solves the knowledge problem by connecting agents to real-time information
• Describe how Foundry IQ provides a shared knowledge platform that multiple agents can access
• Configure data sources for knowledge bases, including Azure AI Search, Blob Storage, SharePoint, and OneLake
• Configure agent statements to control retrieval behavior and ensure consistent citations
• Test and monitor agent recovery to maintain quality in production

Integrate your agent with Microsoft 365

• Explain the options for publishing Foundry agents to Microsoft 365
• Publish an agent from the Foundry portal to Teams and Microsoft 365 Copilot
• Use Work IQ to access Microsoft 365 data in your agents
• Test and troubleshoot Microsoft 365-integrated agents

Create agent-driven workflows using Microsoft Foundry

• Explain how agent nodes, variables, and outputs control workflow execution
• Route queries using structured output and conditional logic
• Loop across multiple inputs with For-Each nodes
• Put a human in the loop and escalation patterns for low-trust items
• Use Power Fx expressions to manipulate data and control flow.

Develop an AI agent with the Microsoft Agent Framework

• Use the Microsoft Agent Framework to connect to a Microsoft Foundry project
• Create Microsoft Foundry Agent service agents by using the Microsoft Agent Framework SDK
• Integrate plug-in features with your AI agent

Orchestrate a multi-agent solution using the Microsoft Agent Framework

• Create AI agents using the Microsoft Agent Framework SDK
• Understand how and when to use different orchestration models
• Develop multi-agent solutions

Discover Azure AI agents with A2A

• Understand the A2A protocol and its role in multi-agent orchestration.
• Design discoverable agents for modular, collaborative problem solving.
• Implement A2A policies to discover and invoke remote agents.

Analyze text with Azure language in Foundry tools

• Describe the Azure Language MCP server and the text analytics capabilities it exposes.
• Explain how MCP enables the discovery and selection of dynamic tools by AI agents.
• Connect the Azure Language MCP server to an agent in Microsoft Foundry.
• Create a Python client application that calls an agent to perform text analysis.

Develop a text analytics agent with the Azure Language MCP server

• Detect the language of the text.
• Recognize named entities in text.
• Extract personally identifiable information (PII) from text.

Develop a generative AI application that supports speech recognition

• Deploy a speech-to-speech-enabled generative AI model in Microsoft Foundry.
• Deploy a generative AI model that supports speech recognition in Microsoft Foundry.
• Use a generative AI model to transcribe speech.
• Use a generative AI model to synthesize voice.

Build apps with speech recognition with Azure Speech in Microsoft Foundry Tools

• Use a Microsoft Foundry resource for Azure Speech in Foundry tools.
• Implement speech recognition with the Azure Speech-to-text API.
• Use the Azure OpenAI SDK to analyze images in Python.
• Use the text-to-speech API to implement text-to-speech.
• Configure the audio format and voices.
• Use the Text-to-Speech Markup Language (SSML).

Develop a speech agent with the Azure Speech MCP server

• Describe the Azure Speech MCP server and the speech capabilities it exposes.
• Explain how MCP enables the discovery and selection of dynamic tools by AI agents.
• Configure Azure Blob Storage for input and output of audio files.
• Connect the Azure Speech MCP server to an agent in Microsoft Foundry.
• Create a Python client application that calls an agent to perform voice tasks.

Develop an Azure Speech Voice Live Agent in Microsoft Foundry

• Describe the key components and features of the Azure Speech Voice Live platform.
• Use the Voice Live API to build conversational AI solutions.
• Use the Voice Live SDK to build and deploy conversational AI solutions.
• Integrate Microsoft Foundry agents with the Voice Live API to create voice agents.

Translate text and speech with Microsoft Foundry tools

• Identify text translation and speech recognition options in Microsoft Foundry Tools.
• Use Azure Translator in Foundry Tools to translate text.
• Use Azure Speech in Foundry Tools to translate speech.

Develop a Vision-Enabled Generative AI Application

• Deploy a vision-enabled generative AI model in Microsoft Foundry.
• Test a picture-based prompt in the conversation playground.
• Create a conversation app that sends image-based prompts.

Generate images using AI

• Describe the features of image generation templates.
• Use the picture playground in the Microsoft Foundry portal.
• Integrate image-building models into your applications.

Generate videos with Microsoft Foundry

• Deploy a video-building AI model in Microsoft Foundry.
• Try a video prompt in the conversation playground.
• Use the Azure OpenIA SDK to generate and remix videos in Python.

Analyze images with Content Understanding

• Deploy a content understanding AI model in Microsoft Foundry.
• Test a picture-based prompt in the conversation playground.
• Use the Azure OpenIA SDK to analyze images in Python.

Build a modal analytics solution with Azure Content Understanding

• Describe the capabilities of Azure Content Understanding.
• Use Azure Content Understanding to create a content analyzer.
• Use a Content Understanding analyzer using the API.

Create an Azure Content Understanding client application

• Use the Azure Content Understanding API to generate a content analyzer.
• Use the Azure Content Understanding API to consume a crawler.

Extract data with Azure Document Intelligence

• Describe the features and components of Azure Document Intelligence.
• Use Document Intelligence Studio to explore and test models.
• Use predefined templates to extract data from common document types.
• Train and use custom templates for industry-specific forms.

Build a knowledge mining solution with Azure AI Search

• Implement indexing with Azure AI Search.
• Use AI capabilities to enrich data in an index.
• Search an index to find relevant information.
• Keep the extracted information in a knowledge base.

Published on 08/18/2026.

In this training, we mix theory with technical workshops to quickly make you operational. Additionally, each participant receives course materials at the end of the training.

One of our consultant trainers conducts the training. With solid field experience, they make the learning process both interactive and enriching.

For assessment, the trainer regularly asks questions and uses various methods to continuously measure your progress. This approach promotes a dynamic and engaging learning experience.

After the training, we ask you to complete a satisfaction questionnaire. Your feedback helps us to maintain and constantly improve the quality of our training.

Finally, we offer the flexibility to deliver this training both in-person and remotely, and it can be customized to meet your company’s specific needs upon request.

You can register for one of our training courses up to two business days before it starts, if there are still available places and you signed quote.

If you have specific needs related to a disability, please do not hesitate to make a request; we are happy to adjust our services according to the type of disability.