September 2026
Intermediate to advanced
260 pages
5h 50m
English
Content preview from Building Agentic Solutions with Microsoft Foundry
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.
Chapter 2. Model Deployment
In this chapter, we’ll learn how to deploy models in Microsoft Foundry. Models are the brains of any AI agentic solution, so picking the right model for your use case and knowing how to deploy it are critical first steps in building agentic solutions.
Microsoft Foundry provides a wide variety of models that you can deploy with just a few clicks or lines of code. You can choose from popular proprietary models from OpenAI and Anthropic, Microsoft-built models like Phi-4 and MAI-Thinking-1, and even open source models from Hugging Face. In addition to the variety, Foundry also provides tools to help you compare models across various benchmarks and metrics to help you pick the best model for your specific use case. Once you’ve picked a model, you can deploy it in just a few minutes without needing to manage any infrastructure. After deployment, you’ll then be able to interact with your model through an API endpoint or through the built-in Playground in the Foundry portal.
Explore Models in the Foundry Portal
Let’s learn how to explore and deploy various AI models from the Foundry Models registry. In later chapters, we’ll also explore some pre-built MCP tools for connecting to data sources.
From the Foundry portal, navigate to the Discover tab at the top of the screen as shown in Figure 2-1.
You’ll see a list of featured models can be deployed. You may notice that some are popular proprietary models like OpenAI’s GPT-5.2 and Anthropic’s Claude Opus 4.5 ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access
More than 5,000 organizations count on O’Reilly
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.Julian F.
I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.Addison B.
I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.Amir M.
I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.