Microsoft Foundry - Part 1
- Nathan
- Aug 14
- 5 min read
Updated: 2 days ago
Microsoft Foundry has everything you need to design, customize, and manage AI applications and agents.
Microsoft Foundry has gone through quite a lot of changes and transformations over a short period of time. Let's go over a quick timeline:
Nov. 2023: Azure AI Studio is released in Public Preview (link)
Nov. 2024: Azure AI Studio is re-branded as Azure AI Foundry (link)
May 2025: Azure AI Foundry is re-launched under a new resource type (link)
This new resource type adds new features versus the old resource type
It also incorporates / is now the new name for Azure AI Services (which is formerly known as Azure Cognitive Services)
Nov. 2025: Azure AI Foundry is re-branded as Microsoft Foundry
The "new" Foundry Portal experience is launched
Azure AI Services is re-branded as Foundry Prebuilt Tools
Here is Microsoft's latest info-graphic on the new Microsoft Foundry:
Part 1 of this series will focus on some of the initial topics that I found confusing to learn and/or understand while I was working with Microsoft Foundry:
I will compare and contrast the old Azure AI Foundry resource type versus the new Microsoft Foundry resource type. For now, both resource types co-exist. I will explain the current state of affairs and which features are available, or not available, on each type. I expect this section to rapidly change over time, and I will try my best to keep this post updated as things change.
I'll cover what I found confusing about both Foundry Models
Finally, I'll cover what I found confusing about Foundry Prebuilt Tools
Microsoft Foundry Resource Types - Old vs. New
Both resource types can create their own connected "Projects". These Projects differ in features and support, as I will outline below.
The old AI Foundry resource type is based on the Azure Resource Provider for "Microsoft.MachineLearningServices/workspaces". With this type, you create an Azure AI Foundry "Hub", and from it you create 1 or more "Hub-based Projects". While this type still exists, it is fairly clear that Microsoft will not be focusing much time or energy on this old resource type. Hub-based Projects still remain accessible for any GenAI capabilities that are not yet supported by the new resource type.
The new Microsoft Foundry resource type is based on the Azure Resource Provider for "Microsoft.CognitiveServices/accounts". You create a Microsoft Foundry resource, and from it you create 1 or more "Foundry Projects". Going forward, new investments and capabilities for Agents and Models will be focused on the new Foundry Projects.
Some quick, rapid-fire observations:
Confusingly, if you deploy the old resource type (Hub) via the Azure Portal, then it will also create the new resource type as well. They will live side by side. The old resource type can connect to, and use features from, the new resource type (more on that below).
When deploying the old resource type (Hub), you will also be required to deploy some dependent resources: a Storage Account, and a Key Vault. However, you can opt to use a Microsoft-managed Key Vault instead (this feature is in Preview)
The Microsoft docs are clear to explain that "Microsoft Foundry projects feature set aren't yet on full parity with AI Foundry Hub-based projects."
Agents are GA in Microsoft Foundry Projects, but are still only Preview in AI Foundry Hub-based Projects
Prompt Flows are only available in AI Foundry Hub-based Projects
The "new" Foundry Portal experience is only available for Microsoft Foundry projects
Foundry Models
Microsoft likes to say that Microsoft Foundry supports over 11,000 AI models. However, that is a little misleading. A model can be "deployed" to Microsoft Foundry in one of three different ways. The vast majority of those 11,000+ models are only available via 1 deployment method: managed compute. Therefore, those models are exclusive to the older AI Foundry Hub-based Projects. That's because, as you can see below, you can only do a Managed Compute deployment when using AI Foundry Hub-based Projects.
If you are using a new Microsoft Foundry Project, then you are only allowed to do what's called a "Standard" deployment. Only a small percentage of the 11,000+ models support the "Standard" deployment.
Note: You can take an old AI Foundry Hub and connect it to a new Microsoft Foundry resource. By doing so, this will unlock the ability to do "Standard" deployments on your old AI Foundry Hub resource.
Some models give you the option of using Provisioned Throughput Units (PTU). PTUs are just generic units of processing capacity. They help by giving you predictable performance, and by providing stable max latency and throughput for uniform workloads. The allocated throughput is available to you whether you use it or not. You can even purchase Azure Reservations for your PTUs to save some cost.
Standard Deployments have 3 different options for data processing, depending on your chosen model:
Global: this will dynamically route traffic to any region across the globe that has the best availability for each request. Global provides the highest default quota and eliminates the need to load balance across multiple resources.
Data-Zone: this will dynamically route traffic to any region within your data-zone that has the best availability for each request. For example, if your AI Foundry resource is deployed to the US, then traffic could be dynamically routed to any region within the US.
Regional: traffic will stay within the region of your AI Foundry. Model availability in each region as well as throughput may be limited.
Foundry Prebuilt Tools
Foundry Prebuilt Tools has now been absorbed by the new Microsoft Foundry resource type. Foundry Prebuilt Tools was previously known as Azure AI Services. And further, Azure AI Services was previously known as Azure Cognitive Services.
When you create a Microsoft Foundry using the new resource type you get an endpoint for your Foundry in the form of https://<foundryName>.cognitiveservices.azure.com. This single endpoint can be used to access many different Azure AI Services:
Azure AI Speech
Azure AI Vision
Azure AI Document Intelligence
Previously known as Azure AI Form Recognizer
Azure AI Language
Azure AI Content Safety
Azure AI Content Understanding
Document Translation
These services are not built into the older AI Foundry Hub resource type. However, you can take an old AI Foundry Hub and connect it to a new Microsoft Foundry resource. By doing so, this will give you access to all of the Foundry Prebuilt Tools in your old AI Foundry Hub.
Conclusion
That covers everything that I was confused about (so far) while I'm going through my journey of learning and using Microsoft Foundry.
Future parts of this series will cover more technical details of Microsoft Foundry's many features and capabilities.