News

Semantic Kernel Agent Framework Graduates to Release Candidate

With agentic AI now firmly established as a key component of modern software development, Microsoft graduated its Semantic Kernel Agent Framework to Release Candidate 1 status.

That was announced last week along with the release of Semantic Kernel 1.40 (.NET) and 1.22.0 (Python).

Semantic Kernel
[Click on image for larger view.] Semantic Kernel (source: Microsoft).

Designed to streamline the development of AI agents for enterprise applications, the Semantic Kernel Agent Framework serves as an extensible and interoperable framework that enables developers to build, orchestrate, and deploy AI-driven agents with various capabilities. It was announced as an experimental project last August (see "Semantic Kernel AI SDK Gets Autonomous Agents (Experimental)").

It builds on functionality such as retrieval augmentation generation (RAG) in the pursuit of fully autonomous agents that can respond to human prompts with minimal human intervention, even interacting with one another to fulfill assigned tasks.

Multiple Agents Interacting
[Click on image for larger view.] Multiple Agents Interacting (source: Microsoft).

"This marks a significant milestone in our journey toward providing a robust, versatile framework for building AI agents for enterprise applications," said Shawn Henry in a post that goes on to demonstrate the code needed to create a Chat Agent with tool plugins.

Plugins and integrations are key to offering, which is not tied to a single AI provider, but rather works with a range of AI services, with Henry highlighting preview functionality for expanded agent provider capabilities, noting Semantic Kernel now supports agents from:

  • Azure AI Agent Service
  • OpenAI Assistants
  • AWS Bedrock
  • Crew AI
  • AutoGen

Those all work with the C# and Python implementations, except for AutoGen, which nows supports only Python, though the team is now focusing on integration with AutoGen.

Developed by Microsoft Research, AutoGen is an open-source framework designed to simplify the creation and management of multi-agent AI systems. It provides tools for defining AI agents that can collaborate, communicate, and perform complex tasks through structured workflows. It's particularly useful for building intelligent agents that leverage large language models (LLMs) like OpenAI’s GPT-4, Azure OpenAI models, and other AI services. For more on that, see the article, "Researchers Take AI Agents to the Next Level with the AutoGen Framework.

About the Author

David Ramel is an editor and writer at Converge 360.

comments powered by Disqus

Featured

  • Semantic Kernel Agent Framework Graduates to Release Candidate

    With agentic AI now firmly established as a key component of modern software development, Microsoft graduated its Semantic Kernel Agent Framework to Release Candidate 1 status.

  • TypeScript 5.8 Improves Type Checking, Conditional Feature Delayed to 5.9

    Microsoft shipped TypeScript 5.8 with improved type checking in some scenarios, but thorny problems caused the dev team to delay related work to the next release.

  • Poisson Regression Using C#

    Dr. James McCaffrey from Microsoft Research presents a complete end-to-end demo of Poisson regression, where the goal is to predict a count of things arriving, such as the number of telephone calls received in a 10-minute interval at a call center. When your source data is close to mathematically Poisson distributed, Poisson regression is simple and effective.

  • Cloud-Focused .NET Aspire 9.1 Released

    Along with .NET 10 Preview 1, Microsoft released.NET Aspire 9.1, the latest update to its opinionated, cloud-ready stack for building resilient, observable, and configurable cloud-native applications with .NET.

  • Microsoft Ships First .NET 10 Preview

    Microsoft shipped .NET 10 Preview 1, introducing a raft of improvements and fixes across performance, libraries, and the developer experience.

Subscribe on YouTube

Upcoming Training Events