Wow! eBook
Microsoft Foundry in Action: A hands-on guide to building, evaluating, and governing enterprise AI agents
Author(s): Eduardo Sojo (Author)
- Publisher: Packt Publishing
- Publication Date: June 26, 2026
- Language: English
- Print length: 370 pages
- ISBN-10: 1835888682
- ISBN-13: 9781835888681
Book Description
Build, deploy, and monitor AI applications using Microsoft Foundry's unified portal, combining models, workflows, agents, and responsible AI practices into a single development experience.
Key Features
- Build, evaluate, and deploy AI solutions using Microsoft Foundry’s unified portal
- Implement guardrails, evaluations, and monitoring for production-ready AI systems
- Includes real-world use cases integrating Azure OpenAI and Databricks
- Purchase of the print or Kindle book includes a free PDF eBook
Book Description
Unlock the full potential of AI with Microsoft Foundry, Microsoft’s unified platform for building, orchestrating, and operating AI solutions at scale. This hands-on guide walks you through the full AI application lifecycle, from data preparation and model selection to deployment, monitoring, and continuous evaluation.
Written by Eduardo Sojo, a former Microsoft consultant and current solutions architect at Databricks with over two decades of experience, the book focuses on practical implementation using the latest Microsoft Foundry portal. You’ll learn to design intelligent workflows, build agents, and apply guardrails to ensure safe, reliable AI behavior in real-world scenarios.
Rather than focusing only on models, the book shows how to connect workflows, agents, evaluations, and observability so solutions are not just functional, but production-ready. You’ll explore real-world use cases such as building copilots, integrating external systems like Databricks, and creating multi-agent architectures that work with enterprise data. By the end, you’ll be able to design, build, and operate secure, scalable, intelligent AI solutions using Microsoft Foundry.
What you will learn
- Select and deploy models for vision, language, and custom AI scenarios
- Use Prompt Flow to design and refine complex AI interactions
- Evaluate models using standard performance metrics
- Build assistants, copilots, and image-processing solutions with Azure OpenAI
- Design, deploy, and orchestrate multi-agent systems using Microsoft Foundry Agent Service
- Utilize Microsoft Foundry Observability for real-time monitoring and evaluation
- Apply Microsoft's Responsible AI principles to real applications
Who this book is for
This book is for developers, data professionals, and AI practitioners who want to build and deploy intelligent applications using Microsoft Foundry. Whether you're transitioning from Azure AI Studio or starting fresh, this guide will help you understand how to design real-world AI systems using modern tools and best practices. Basic knowledge of programming and data concepts will help you get the most out of this book.
Table of Contents
- Introduction to Microsoft Foundry
- Delving Deeper into Microsoft Foundry's Features
- Working with Data
- Choosing the Right Model
- Working with Workflows
- Deploying AI Solutions
- Evaluating and Monitoring AI Applications
- Implementing Responsible AI Principles
- Ensuring Content Safety and Compliance
- Building Assistants and Copilots
- Creating Custom Copilots with Microsoft Fabric
- Building an Agent that Uses Databricks Genie via MCP
Editorial Reviews
Review
“Learning Microsoft AI Foundry is a practical guide for anyone looking to understand Microsoft's AI platform beyond the basics. Eduardo Sojo explains key concepts like AI agents, orchestration, evaluation, monitoring, and responsible AI in a clear and structured way. What I appreciated most is the book's focus on building real-world AI solutions rather than just explaining features. It's an excellent resource for developers, architects, data professionals, and technical leaders who want to move from AI experimentation to production with confidence.”
David Sanchez Aguilar
Director, Go-to-Market – Azure Developer Audience, Microsoft
“Learning Microsoft AI Foundry is a practical guide for teams looking to build production-ready AI applications with Microsoft AI Foundry. Eduardo Sojo takes readers through the complete lifecycle from data and RAG to agents, evaluation, monitoring, governance, and Responsible AI. What makes this book valuable is its end-to-end, hands-on approach. Rather than focusing only on deployment, it explains what is needed to build reliable, secure, and scalable AI solutions. It's a great resource for developers, architects, data engineers, and platform teams adopting AI in enterprise environments.”
Massimo Bonanni
Microsoft Technical Trainer & Business Program Manager, Microsoft
“Learning Microsoft AI Foundry offers a clear and practical introduction to building AI solutions with Microsoft's AI platform. Eduardo Sojo explains key concepts such as AI agents, RAG, workflows, deployment, monitoring, governance, and Responsible AI in an easy-to-follow manner. The book goes beyond theory by connecting these topics to real-world scenarios, making it especially valuable for consultants, architects, AI engineers, and professionals preparing for Microsoft AI certifications or implementing Azure AI solutions in practice.”
Sabih Ahmed Khan
Power Platform & Azure Cloud Administrator, Texas General Land Office
About the Author
Eduardo Sojo is a Solutions Architect at Databricks and a former Microsoft consultant with over 15 years of experience designing and delivering data and AI solutions across industries such as banking, telecommunications, and retail. Throughout his career, Eduardo has evolved from application development into data engineering, analytics, and artificial intelligence, working hands-on with technologies ranging from traditional BI systems to modern lakehouse architectures and generative AI platforms. He specializes in building practical, scalable solutions that bridge the gap between business needs and modern AI capabilities. Having worked closely with enterprise customers, Eduardo brings real-world insights into how AI systems are actually designed, deployed, and operated in production. In this book, he shares a hands-on approach to Microsoft Foundry, helping readers move beyond theory and build AI solutions that deliver real value.
