Microsoft Foundry Essentials: RAG, Fine-Tuning and AI Agents

Whizlabs via Coursera

Go to class Write review

Overview

Google, IBM & Meta Certificates – 40% Off

One plan covers every Professional Certificate on Coursera.

Unlock All Certificates

The Microsoft Foundry Essentials: RAG, Fine-Tuning, and AI Agents course is designed for AI developers, machine learning engineers, software developers, data professionals, and cloud practitioners who want to build practical skills in developing, customizing, and deploying generative AI applications using Microsoft Foundry and Azure Machine Learning. This course introduces learners to the end-to-end lifecycle of foundation model customization, Retrieval-Augmented Generation (RAG), and AI agent development using Microsoft Foundry. You will explore how to prepare datasets, fine-tune foundation models, evaluate model performance, deploy models to managed endpoints, and validate deployments in Azure Machine Learning. You’ll also learn how Microsoft Foundry simplifies generative AI development through its unified portal, model catalog, playgrounds, evaluation capabilities, governance features, and model optimization workflows. The course covers Retrieval-Augmented Generation (RAG), application design strategies, and the process of creating and testing customized AI models using Microsoft Foundry. Finally, you’ll explore Microsoft Foundry projects, hubs, Azure AI Search integration, Agent Service, and the Microsoft Foundry SDK to build, test, and integrate AI agents into real-world applications. Through a combination of conceptual explanations, guided demonstrations, and hands-on implementation, you’ll gain practical experience building production-ready AI solutions using Microsoft’s AI development platform. The course delivers approximately 5+ hours of structured video content, organized into three modules. Each module includes quizzes and knowledge checks to reinforce learning and validate understanding. Enroll in this course to build a strong foundation in Retrieval-Augmented Generation (RAG), model fine-tuning, and AI agent development, and confidently create intelligent applications using Microsoft Foundry and Azure Machine Learning. Course Modules: Module 1: Fine-Tuned Model Deployment and Testing in Azure ML Module 2: Microsoft Foundry Portal and AI Model Fine-Tuning Module 3: Microsoft Foundry Projects, Agents, and SDK Integration By the End of This Course, You Will Be Able To: - Understand the end-to-end lifecycle of foundation model fine-tuning. - Prepare datasets for model customization in Azure Machine Learning. - Deploy, evaluate, and validate fine-tuned foundation models. - Navigate Microsoft Foundry Portal and use the Model Catalog effectively. - Build Retrieval-Augmented Generation (RAG) solutions using Microsoft Foundry. - Compare fine-tuning and RAG strategies for different AI application scenarios. - Configure projects, hubs, quotas, and resources within Microsoft Foundry. - Integrate Azure AI Search into generative AI applications. - Create, test, and deploy AI agents using Microsoft Foundry Agent Service. - Build and integrate AI-powered applications using the Microsoft Foundry SDK.

Syllabus

Fine-Tuned Model Deployment and Testing in Azure ML

In this section, you'll learn how to deploy, validate, and test fine-tuned AI models using Azure Machine Learning. You'll begin by preparing high-quality training datasets and importing them into Azure Machine Learning, establishing the foundation for successful model deployment and evaluation. As you progress, you'll explore foundation models available in Azure Machine Learning and learn how to select the most appropriate model based on your application requirements. You'll then deploy fine-tuned models to managed endpoints, gaining practical experience with the deployment workflow and understanding the key considerations for serving AI models in production environments. The section also focuses on validating deployed models by testing inference endpoints and evaluating model responses. You'll learn how to identify and troubleshoot common deployment and endpoint issues, ensuring that fine-tuned models perform reliably and meet application requirements. By the end of this section, you'll have a solid understanding of the end-to-end deployment process for fine-tuned models in Azure Machine Learning, from dataset preparation and model deployment to endpoint testing and troubleshooting, enabling you to confidently deploy and validate enterprise-ready AI solutions.

Microsoft Foundry Portal and AI Model Fine-Tuning

In this section, you'll build a strong foundation in Microsoft Foundry and learn how to develop, optimize, and evaluate generative AI models using Azure AI services. You'll begin by exploring the Microsoft Foundry Portal, including the Model Catalog, AI playgrounds, and development tools, to understand how Microsoft Foundry supports the end-to-end AI development lifecycle.As you progress, you'll explore Retrieval-Augmented Generation (RAG) and learn how it enhances generative AI applications by combining foundation models with external knowledge sources. You'll examine the differences between RAG and model fine-tuning, understand when to use each approach, and explore practical strategies for optimizing AI applications based on different business and technical requirements. The section further introduces model optimization techniques using Microsoft Foundry. You'll learn how to create AI playgrounds, fine-tune foundation and OpenAI models, and evaluate the performance of customized models through guided demonstrations. You'll also gain insight into AI evaluation, governance, and monitoring capabilities that help ensure models remain reliable, efficient, and ready for enterprise deployment.By the end of this section, you'll have a solid understanding of Microsoft Foundry's AI development capabilities, Retrieval-Augmented Generation (RAG), model fine-tuning workflows, and the tools required to build, optimize, and evaluate enterprise-ready generative AI solutions.

Microsoft Foundry Projects, Agents, and SDK Integration

In this section, you'll learn how to organize AI development projects, manage resources, and build intelligent AI agents using Microsoft Foundry. You'll begin by exploring Microsoft Foundry hubs, projects, and the resources required to support AI development. You'll also learn about access control, project organization, quotas, and token management to effectively manage AI workloads within Microsoft Foundry. As you progress, you'll discover how Azure AI Search enhances generative AI applications by enabling intelligent search and retrieval capabilities. You'll learn how to create and configure a search index in the Azure portal, providing the foundation for building AI applications that leverage enterprise knowledge and Retrieval-Augmented Generation (RAG) scenarios. The section then focuses on building intelligent AI agents using Microsoft Foundry Agent Service. You'll gain hands-on experience creating and testing AI agents before integrating them into applications using the Microsoft Foundry SDK. Through guided demonstrations, you'll learn how to execute projects, configure agent workflows, and enable seamless communication between AI agents and external applications. By the end of this section, you'll have a solid understanding of Microsoft Foundry resource management, Azure AI Search integration, AI agent development, and SDK-based application integration, enabling you to build, deploy, and manage intelligent, enterprise-ready AI solutions.