Update .NET AI ecosystem docs to feature Microsoft Agent Framework #49616
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Co-authored-by: gewarren <[email protected]>
Copilot
AI
changed the title
[WIP] Update article to describe Agent Framework instead of Semantic Kernel
Update .NET AI ecosystem docs to feature Microsoft Agent Framework
Nov 4, 2025
Copilot finished work on behalf of
gewarren
November 4, 2025 21:00
gewarren
approved these changes
Nov 4, 2025
docs/ai/dotnet-ai-ecosystem.md
Outdated
|
|
||
| If you just want to use the low-level services, such as <xref:Microsoft.Extensions.AI.IChatClient> and <xref:Microsoft.Extensions.AI.IEmbeddingGenerator`2>, you can reference the `Microsoft.Extensions.AI.Abstractions` package directly from your app. However, if you want to build agentic AI applications with higher-level orchestration capabilities, you should use [Microsoft Agent Framework](/agent-framework/overview/agent-framework-overview). | ||
|
|
||
| Microsoft Agent Framework is a production-ready, open-source framework that brings together the best capabilities of Semantic Kernel and Microsoft Research's AutoGen. The Agent Framework provides: |
There was a problem hiding this comment.
Suggested change
| Microsoft Agent Framework is a production-ready, open-source framework that brings together the best capabilities of Semantic Kernel and Microsoft Research's AutoGen. The Agent Framework provides: | |
| Microsoft Agent Framework is a production-ready, open-source framework that brings together the best capabilities of Semantic Kernel and Microsoft Research's AutoGen. Agent Framework provides: |
There was a problem hiding this comment.
Updated in 85e747c
docs/ai/dotnet-ai-ecosystem.md
Outdated
| - **Enterprise-grade features**: Built-in observability (OpenTelemetry), Microsoft Entra security integration, and responsible AI features including prompt injection protection and task adherence monitoring. | ||
| - **Standards-based interoperability**: Integration with open standards like Agent-to-Agent (A2A) protocol and Model Context Protocol (MCP) for agent discovery and tool interaction. | ||
|
|
||
| The Agent Framework builds on the `Microsoft.Extensions.AI.Abstractions` package and provides concrete implementations of <xref:Microsoft.Extensions.AI.IChatClient> for different services, including OpenAI, Azure OpenAI, Azure AI Foundry, and more. |
There was a problem hiding this comment.
Suggested change
| The Agent Framework builds on the `Microsoft.Extensions.AI.Abstractions` package and provides concrete implementations of <xref:Microsoft.Extensions.AI.IChatClient> for different services, including OpenAI, Azure OpenAI, Azure AI Foundry, and more. | |
| Agent Framework builds on the `Microsoft.Extensions.AI.Abstractions` package and provides concrete implementations of <xref:Microsoft.Extensions.AI.IChatClient> for different services, including OpenAI, Azure OpenAI, and Azure AI Foundry. |
There was a problem hiding this comment.
Updated in 85e747c
docs/ai/dotnet-ai-ecosystem.md
Outdated
| Microsoft Agent Framework is a production-ready, open-source framework that brings together the best capabilities of Semantic Kernel and Microsoft Research's AutoGen. The Agent Framework provides: | ||
|
|
||
| - **Multi-agent orchestration**: Support for sequential, concurrent, group chat, handoff, and magnetic orchestration patterns. | ||
| - **Cloud and provider flexibility**: Cloud-agnostic (containers, on-premises, or multi-cloud) and provider-agnostic (OpenAI, Azure AI Foundry, and more) using plugin and connector models. |
There was a problem hiding this comment.
Suggested change
| - **Cloud and provider flexibility**: Cloud-agnostic (containers, on-premises, or multi-cloud) and provider-agnostic (OpenAI, Azure AI Foundry, and more) using plugin and connector models. | |
| - **Cloud and provider flexibility**: Cloud-agnostic (containers, on-premises, or multi-cloud) and provider-agnostic (for example, OpenAI or Azure AI Foundry) using plugin and connector models. |
There was a problem hiding this comment.
Updated in 85e747c
docs/ai/dotnet-ai-ecosystem.md
Outdated
| ## Develop with local AI models | ||
|
|
||
| .NET apps can also connect to local AI models for many different development scenarios. [Semantic Kernel](https://github.com/microsoft/semantic-kernel) is the recommended tool to connect to local models using .NET. Semantic Kernel can connect to many different models hosted across a variety of platforms and abstracts away lower-level implementation details. | ||
| .NET apps can also connect to local AI models for many different development scenarios. [Microsoft Agent Framework](https://github.com/microsoft/agent-framework) and [Semantic Kernel](https://github.com/microsoft/semantic-kernel) are recommended tools to connect to local models using .NET. These frameworks can connect to many different models hosted across a variety of platforms and abstract away lower-level implementation details. |
There was a problem hiding this comment.
Suggested change
| .NET apps can also connect to local AI models for many different development scenarios. [Microsoft Agent Framework](https://github.com/microsoft/agent-framework) and [Semantic Kernel](https://github.com/microsoft/semantic-kernel) are recommended tools to connect to local models using .NET. These frameworks can connect to many different models hosted across a variety of platforms and abstract away lower-level implementation details. | |
| .NET apps can also connect to local AI models for many different development scenarios. [Microsoft Agent Framework](https://github.com/microsoft/agent-framework) is the recommended tool to connect to local models using .NET. This framework can connect to many different models hosted across a variety of platforms and abstracts away lower-level implementation details. |
There was a problem hiding this comment.
Updated in 85e747c
Co-authored-by: gewarren <[email protected]>
Copilot finished work on behalf of
gewarren
November 4, 2025 22:20
gewarren
reviewed
Nov 4, 2025
gewarren
approved these changes
Nov 4, 2025
There was a problem hiding this comment.
Pull Request Overview
This PR updates the .NET AI ecosystem documentation to introduce Microsoft Agent Framework as a new recommended approach for building agentic AI applications. The update positions Agent Framework as the primary choice for advanced multi-agent orchestration while clarifying that Semantic Kernel remains suitable for simpler AI integration scenarios.
- Adds a new section introducing Microsoft Agent Framework and its capabilities.
- Updates guidance on when to use Semantic Kernel versus Agent Framework.
- Updates the SDK comparison table and local AI model recommendations to include Agent Framework.
Co-authored-by: Copilot <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
The article focused primarily on Semantic Kernel, but Microsoft Agent Framework is now the production-ready framework combining Semantic Kernel and AutoGen capabilities for agentic AI development.
Changes
Microsoft.Agents.AI.OpenAIpackage as first entryThe documentation now reflects Microsoft's current strategy where Agent Framework is recommended for new agentic applications requiring advanced orchestration, while Semantic Kernel remains suitable for simpler AI integration scenarios.
Original prompt
💬 We'd love your input! Share your thoughts on Copilot coding agent in our 2 minute survey.
Internal previews