On the coronary heart of Microsoft’s AI utility improvement technique is Semantic Kernel, an open source set of instruments for managing and orchestrating AI prompts. Since its launch as a strategy to simplify constructing retrieval-augmented generation (RAG) functions, it has grown right into a framework for constructing and managing agentic AI.
At Ignite in 2024, Microsoft introduced a number of new options for Semantic Kernel, positioning it as its most well-liked instrument for constructing large-scale agentic AI functions. That announcement fashioned the idea of Semantic Kernel’s 2025 road map, with the primary components already being delivered.
Constructing agentic workflows with Agent Framework
One of many extra necessary new options in Semantic Kernel is Agent Framework, which can quickly transfer out of preview into common availability. It will guarantee a secure, supported set of instruments able to ship production-grade enterprise AI functions. The Agent Framework will type the idea of Semantic Kernel’s deliberate integration with Microsoft Research’s AutoGen, together with the discharge of a standard runtime for brokers that’s constructed utilizing each platforms.
The Agent Framework is intended to help build applications around agent-like patterns, providing a method so as to add autonomy to functions and to ship what Microsoft calls “goal-oriented functions.” This can be a good definition of what trendy agentic AI must be: a method of utilizing AI instruments to assemble and handle a workflow based mostly on a consumer request. It then permits a number of brokers to collaborate, sharing information and managing what may be regarded as lengthy transactions that work throughout many various utility APIs and endpoints.
Obtainable as an extension to the bottom Semantic Kernel, the Agent Framework is delivered as a set of .NET libraries, which assist handle human/agent interactions and supply entry to OpenAI’s Assistant API. It’s supposed to be managed by way of dialog, although it’s simple sufficient to construct and run brokers that reply to system occasions somewhat than direct human actions (and so as to add human approval steps as a part of a dynamic workflow). This allows you to deal with utilizing brokers to handle duties.
Semantic Kernel’s agent options are designed to increase the ideas and instruments used to construct RAG-powered AI workflows. As at all times, Semantic Kernel is how each the general orchestration and particular person brokers run, managing context and state in addition to dealing with calls to AI endpoints by way of Azure AI Foundry and comparable companies.
Building a Semantic Kernel agent requires an Agent class earlier than utilizing an Agent Chat to assist interactions between your agent workflow and the AI and API endpoints used to finish the present activity. If a number of brokers should be known as, you need to use an Agent Group Chat to handle these inner prompts by utilizing Semantic Kernel to work together and go outcomes between one another. An Agent Group Chat may be dynamic, including and eradicating participant brokers as wanted.
You’re capable of construct on current Semantic Kernel methods, too. For instance, brokers can use current or new plug-ins in addition to name capabilities. Working with exterior functions is essential to constructing enterprise brokers, as they want to have the ability to dynamically generate workflows round each people and software program.
Having Semantic Kernel handle brokers ensures you possibly can handle each directions and prompts for the large language model (LLM) you’re utilizing, in addition to management entry to the APIs. Your code can handle authorization as obligatory and add plug-in objects. Your plug-ins will handle API calls, with the agent setting up queries by parsing consumer inputs.
No-code agent improvement with AutoGen
Semantic Kernel’s integration with AutoGen builds on its Process Framework. That is designed to handle long-running enterprise processes and works with distributed utility frameworks resembling Dapr and Orleans. Workflows are event-driven, with steps constructed round Semantic Kernel Capabilities. A process isn’t an agent, as it’s a defined workflow and there is no self-orchestration. Nonetheless, a step can include an agent if it has well-defined inputs and outputs. Processes can benefit from widespread patterns, and there’s no purpose to have capabilities function sequentially—they’ll run asynchronously in parallel, permitting you to have flows that fan out or that rely upon a number of inputs.
The 2 platforms converge of their use of Orleans, which ensures they’ve comparable approaches to working in event-driven environments. This is a vital basis, as Orleans’ transfer from being a Microsoft Analysis venture to being the foundational distributed computing structure for contemporary .NET has been key to wider uptake.
Utilizing AutoGen as a part of its agent tooling will assist ship higher assist for multi-agent operations in Semantic Kernel. Because it’s been a analysis venture, there’s nonetheless some work essential to carry the 2 platforms collectively, with AutoGen supporting each .NET and Python, very similar to Semantic Kernel.
Definitely AutoGen simplifies the method of constructing brokers, with a no-code GUI and support for a variety of different LLMs resembling OpenAI (and Azure OpenAI). There’s additionally assist for Ollama, Azure Foundry-hosted fashions, Gemini, and a Semantic Kernel adapter that allows you to use Sematic Kernel’s mannequin shoppers.
Getting began with AutoGen requires the core AutoGen application and a model client. As soon as put in, you possibly can construct a easy agent with a handful of strains of code. Issues get attention-grabbing while you construct a multi-agent utility or, as AutoGen calls it, a staff. Groups are introduced collectively in a bunch chat the place customers give brokers duties. It comes with prebuilt brokers that can be utilized as constructing blocks, resembling a consumer proxy, an online surfer, or an assistant.
You may shortly add your personal extensions to customise actions throughout the AutoGen layered framework. This offers particular roles for components of an agent, beginning with the core API that gives instruments for occasion dealing with and messaging, providing you with an asynchronous hub for agent operations. Above that’s the AgentChat API. That is designed that will help you shortly construct brokers utilizing prebuilt parts and your personal code, in addition to instruments for dealing with directions and prompts. Lastly, the Extensions API is the place you possibly can add assist for each new LLMs and your personal code.
A lot of the documentation focuses on Python. Though there’s a .NET implementation of AutoGen, it’s missing documentation for key features such as AgentChat. Even so, .NET is probably going the perfect instrument to construct brokers that run throughout distributed techniques, utilizing its assist for .NET Aspire and, by way of that, frameworks like Dapr.
Constructing multi-agent groups in AutoGen Studio
AutoGen Studio is perhaps the most interesting part and would work nicely as a part of the Semantic Kernel Visible Studio Code extension. It installs as a neighborhood internet utility and offers a spot to assemble groups of brokers and extensions, with the intention of setting up a multi-agent utility while not having to jot down any further code (although you need to use it to edit generated-configuration JSON). It builds on high of AutoGen’s AgentChat service.
Purposes are constructed by dragging parts onto the Studio canvas and including termination circumstances. This final possibility is necessary: That is how an agent “is aware of” it has accomplished a activity and must ship outcomes to both a consumer or a calling operate. Brokers may be additional configured by including fashions and extensions, for instance, utilizing an extension to ship a RAG question towards enterprise information. A number of mannequin assist helps you select an acceptable AI mannequin for an agent, maybe one which’s been fine-tuned or that gives multi-model actions so you possibly can work with pictures and audio in addition to textual content prompts. Nodes in a staff may be edited so as to add parameters the place obligatory.
Beneath the hood, AutoGen is a declarative agent improvement atmosphere, with JSON description of the varied components that go into making an agent. You may change to a JSON view to make adjustments and even convert AutoGen AgentChat Python to JSON and edit it in Studio. To simplify constructing new functions, it presents a gallery the place brokers and different parts may be shared with different customers. When you’ve constructed an agent, you possibly can consider it inside Studio’s playground earlier than constructing it into a bigger course of.
Utilizing declarative programming techniques to construct agent groups is sensible; usually the data wanted to assemble components of a workflow or enterprise course of is embedded within the course of itself as data passes from employee to employee. If we’re to construct AI-based brokers to automate components of these processes, who higher to design these duties than the individuals who know precisely what must be finished?
There’s so much but to come back for Semantic Kernel in 2025. Now that we’re popping out of the experimental part of enterprise AI the place we used chatbots to discover ways to construct efficient prompts, it’s time to make use of these classes to construct workflow instruments extra suited to the multi-channel, multi-event processes that type the spine of our companies. Semantic Kernel is beginning to step out into the enterprise IT world. It’ll be attention-grabbing to look at the way it and AutoGen benefit from the talents and data that exist throughout our organizations, past IT and improvement groups.