How can you create autonomous AI agents capable of executing complex tasks and interacting with your enterprise systems? AI agents represent the next evolution of artificial intelligence: beyond simple conversation, they plan, reason and act to accomplish objectives. But building reliable agents that integrate with your existing infrastructure requires mastering the right tools and architectures.
The AI-3026 training teaches you to design, develop and deploy AI agents with Azure AI Foundry and Microsoft Copilot Studio. In one intensive day, you create agents capable of orchestrating multiple tools, accessing your enterprise data through plugins and making contextualized decisions. You discover how to combine the power of Azure OpenAI models with Copilot Studio connectors for production-ready agents. This official Microsoft course, delivered by MCT trainers at ITTA in Geneva or Lausanne, positions you on one of the most in-demand AI skills for 2025-2026.
Module 1 : Develop AI agents with Microsoft Foundry and Visual Studio Code
Module 2 : Integrate custom tools into your agent
Module 3 : Integrate MCP Tools with Azure AI Agents
Module 4 : Build knowledge-enhanced AI agents with Foundry IQ
Module 5 : Integrate your agent with Microsoft 365
Module 6 : Build agent-driven workflows using Microsoft Foundry
Module 7 : Develop an AI agent with Microsoft Agent Framework
Module 8 : Orchestrate a multi-agent solution using the Microsoft Agent Framework
Module 9 : Discover Azure AI Agents with A2A
AI agents represent a turning point in the use of artificial intelligence in the enterprise. Unlike classic chatbots that are limited to answering questions, AI agents can plan sequences of actions, use external tools, access databases, and make autonomous decisions to achieve a defined objective. This capacity to act — not just converse — opens up considerable possibilities for automating business processes.
The AI-3026 training places you at the heart of this revolution by teaching you to build agents using Microsoft’s two flagship platforms: Azure AI Foundry (formerly Azure AI Studio) for advanced code-based agents, and Copilot Studio for low-code agents accessible to business analysts. You will understand when to use each approach and how to combine them to address your organization’s needs.
Azure AI Foundry is Microsoft’s unified platform for developing AI applications and agents. It provides a complete environment for prototyping, testing, and deploying agents powered by Azure OpenAI models. You have an interactive playground for rapidly iterating on your agent’s behavior, an SDK for programmatic development, and monitoring tools to track performance in production.
During the training, you create an agent in Azure AI Foundry by defining its system instruction, available tools, and orchestration logic. You learn to connect the agent to custom functions that interact with your APIs and databases. You discover how to manage conversational context, implement safety guardrails, and evaluate the quality of the agent’s responses through structured test scenarios.
Microsoft Copilot Studio democratizes AI agent creation with a visual design interface. Business analysts and power users can build sophisticated conversational agents, connect them to data sources via Power Platform connectors, and publish them on Teams, websites, or other channels. Copilot Studio natively handles natural language understanding and dialog orchestration.
The training shows you how to create an agent in Copilot Studio, define its topics and conversation flows, and extend its capabilities with plugins and custom actions. You learn to integrate enterprise knowledge so the agent responds based on your internal documents. You also discover how to connect Copilot Studio agents to those built in Azure AI Foundry, combining the power of code with the simplicity of low-code.
The value of an AI agent lies in its ability to interact with the outside world. Plugins and connectors allow your agents to access APIs, read and write to databases, send emails, create tickets, or trigger Power Automate workflows. The training teaches you to design these extensions in a secure and performant manner.
You work on multi-step orchestration, where the agent breaks down a complex objective into sub-tasks that it executes sequentially or in parallel. You learn to handle errors, timeouts, and edge cases to build robust and reliable agents. ITTA’s MCT instructors share proven architecture patterns for production agents and the pitfalls to avoid during development.
ITTA, a Microsoft Learning Partner in French-speaking Switzerland, delivers this training at its Geneva and Lausanne centers as well as in a virtual classroom. MCT-certified instructors combine Azure expertise with practical experience in AI agent development. The official Microsoft course materials (MOC) are included, along with access to Azure cloud labs. Basic knowledge of Azure and generative AI concepts is recommended to get the most out of this one-day course.
What is the difference between Azure AI Foundry and Copilot Studio?
Azure AI Foundry is a development platform for advanced agents requiring code and in-depth customization. Copilot Studio is a low-code solution for quickly building conversational agents. The two platforms are complementary.
Do I need programming skills to attend this training?
Basic development knowledge is recommended for the Azure AI Foundry section. The Copilot Studio section is accessible without programming skills. The training covers both approaches.
Can the agents access our company’s data?
Yes, agents can connect to your data sources via secure plugins and connectors. The training covers configuring these connections with appropriate authentication and authorization controls.
What is the difference between an AI agent and a classic chatbot?
A chatbot follows predefined scenarios and answers questions. An AI agent can reason, plan actions, use tools, and make autonomous decisions to achieve a goal — making it capable of handling much more complex tasks.
Are the agents built during the training deployable in production?
The agents built during the labs serve as functional prototypes. You learn the best practices for evolving them toward a production deployment, including security, monitoring, and performance management.
How do agents handle security and privacy?
Azure AI Foundry and Copilot Studio both include native security features: authentication, authorization, data encryption, and content guardrails. The training covers configuring these mechanisms for a secure deployment.
Monday to Friday
8:30 AM to 6:00 PM
Tel. 058 307 73 00
ITTA
Route des jeunes 35
1227 Carouge, Suisse
Monday to Friday, from 8:30 am to 06:00 pm.
