MS-4019: Transform your everyday business processes with agents
This course provides a comprehensive foundation in the principles of Generative AI and the practical skills necessary to build custom AI-powered assistants. Participants will begin by exploring the core concepts of Large Language Models (LLMs), effective prompting strategies, and the architecture of AI Agents.
The majority of the training is dedicated to hands-on experience using Microsoft Copilot Studio, where learners will be guided through setting up environments, designing conversational flows, implementing productivity enhancements with Generative AI features, and ultimately publishing and analyzing their own custom agents.
This course is designed for:
- Developers and Technical Architects
- Business Analysts and Product Managers
- Power Platform Enthusiasts
By the end of the course, participants should be able to:
- Explain the core roles of Large Language Models (LLMs), interpret basic prompt engineering techniques, and differentiate between various generative AI agent scenarios.
- Effectively navigate the Microsoft Copilot Studio interface to create, design, publish, and manage a functional AI agent tailored to a specific business need.
- Apply prompting strategies and Copilot Studio features to enhance agent productivity, analyze performance data, and ensure efficient, high-quality conversational interactions.
- Identify the critical planning, preparation, and environmental considerations necessary to develop and deploy scalable, secure, AI-powered solutions on the Microsoft Azure platform.
Module 01: Introduction to Generative AI and Agents
Generative AI powers applications that can create content, answer questions, and assist with tasks. In this module, you'll explore the fundamentals of generative AI, including large language models (LLMs), prompts, and AI agents.
Topics
- Large language models (LLMs)
- Prompts
- AI agents
- Exercise: Explore generative AI agent scenarios
Module 02: Get started with Microsoft Copilot Studio
Microsoft Copilot Studio allows organizations to quickly create agents based on business scenarios their customers and employees can easily interact with as needed. In this module, you're introduced to key concepts for agents.
Topics
- Get started working with environments
- Create agents and work with the Microsoft Copilot Studio interface
- Create topics
- Enhancing productivity with Generative AI
- Test your agents
- Publish agents and analyze performance 5 min
- Exercise: Create an agent with Microsoft Copilot Studio
Module 03: Plan and prepare to develop AI solutions on Azure
Microsoft Azure offers multiple services that enable developers to build amazing AIpowered solutions. Proper planning and preparation involves identifying the services you'll use and creating an optimal working environment for your development team.
Topics
- What is AI?
- Azure AI services
- Azure AI Foundry
- Developer tools and SDKs
- Responsible AI
- Exercise: Prepare for an AI development project
Module 04: Develop a RAG-based solution with your own data using Azure AI Foundry
Retrieval Augmented Generation (RAG) is a common pattern used in generative AI solutions to ground prompts with your data. Azure AI Foundry provides support for adding data, creating indexes, and integrating them with generative AI models to help you build RAG-based solutions.
Topics
- Understand how to ground your language model
- Make your data searchable
- Create a RAG-based client application
- Implement RAG in a prompt flow
- Exercise: Create a generative AI app that uses your own data
