On the coronary heart of Microsoft’s AI utility improvement technique is Semantic Kernel, an open supply set of instruments for managing and orchestrating AI prompts. Since its launch as a option to simplify constructing retrieval-augmented era (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 popular software for constructing large-scale agentic AI functions. That announcement fashioned the premise of Semantic Kernel’s 2025 highway map, with the primary parts already being delivered.
One of many extra essential new options in Semantic Kernel is the Agent Framework, which is able to quickly transfer out of preview into normal availability. This can guarantee a steady, supported set of instruments able to ship production-grade enterprise AI functions. The Agent Framework will kind the premise of Semantic Kernel’s deliberate integration with Microsoft Analysis’s AutoGen, together with the discharge of a typical runtime for brokers that’s constructed utilizing each platforms.
Constructing agentic workflows with the Agent Framework
The Agent Framework is meant to assist construct functions round agent-like patterns, providing a manner so as to add autonomy to functions and to ship what Microsoft calls “goal-oriented functions.” This can be a good definition of what fashionable agentic AI needs to be: a manner of utilizing AI instruments to assemble and handle a workflow primarily based on a person request. It then permits a number of brokers to collaborate, sharing information and managing what might be considered 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 through dialog, although it’s simple sufficient to construct and run brokers that reply to system occasions quite 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 through Azure AI Foundry and related providers.
Brokers speaking to brokers
Constructing 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 must be known as, you should utilize an Agent Group Chat to handle these inside prompts by utilizing Semantic Kernel to work together and cross outcomes between one another. An Agent Group Chat might be dynamic, including and eradicating participant brokers as wanted.
You’re in a position to construct on present Semantic Kernel strategies, too. For instance, brokers can use present or new plug-ins in addition to name capabilities. Working with exterior functions is vital 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’ll be able to handle each directions and prompts for the massive language mannequin (LLM) you’re utilizing, in addition to management entry to the APIs. Your code can handle authorization as essential and add plug-in objects. Your plug-ins will handle API calls, with the agent developing queries by parsing person inputs.
No-code brokers with AutoGen
Semantic Kernel’s integration with AutoGen builds on its Course of Framework. That is designed to handle long-running enterprise processes and works with distributed utility frameworks equivalent to Dapr and Orleans. Workflows are event-driven, with steps constructed round Semantic Kernel Capabilities. A course of isn’t an agent, because it’s an outlined workflow and there’s no self-orchestration. Nonetheless, a step can comprise an agent if it has well-defined inputs and outputs. Processes can make the most of 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 on a number of inputs.
The 2 platforms converge of their use of Orleans, which ensures they’ve related approaches to working in event-driven environments. This is a crucial 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 deliver the 2 platforms collectively, with AutoGen supporting each .NET and Python, very like Semantic Kernel.
Definitely AutoGen simplifies the method of constructing brokers, with a no-code GUI and assist for a wide range of totally different LLMs equivalent to OpenAI (and Azure OpenAI). There’s additionally assist for Ollama, Azure Foundry-hosted fashions, Google Gemini, and a Semantic Kernel adapter that allows you to use Semantic Kernel’s mannequin shoppers.
Getting began with AutoGen
Getting began with AutoGen requires the core AutoGen utility and a mannequin shopper. As soon as put in, you’ll be able to construct a easy agent with a handful of strains of code. Issues get attention-grabbing whenever you construct a multi-agent utility or, as AutoGen calls it, a group. 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, equivalent to a person proxy, an online surfer, or an assistant.
You possibly can shortly add your personal extensions to customise actions inside the AutoGen layered framework. This gives particular roles for parts of an agent, beginning with the core API that gives instruments for occasion dealing with and messaging, supplying 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 elements and your personal code, in addition to instruments for dealing with directions and prompts. Lastly, the Extensions API is the place you’ll be able to 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 lacking documentation for key options equivalent to AgentChat. Even so, .NET is probably going the perfect software to construct brokers that run throughout distributed techniques, utilizing its assist for .NET Aspire and, by Aspire, frameworks like Dapr.
Constructing brokers in AutoGen Studio
AutoGen Studio is maybe essentially the most attention-grabbing half and would work properly as a part of the Semantic Kernel extension for Visible Studio Code. It installs as an area net utility and gives a spot to assemble groups of brokers and extensions, with the goal of developing a multi-agent utility without having to jot down any further code (although you should utilize it to edit generated-configuration JSON). It builds on high of AutoGen’s AgentChat service.
Purposes are constructed by dragging elements onto the AutoGen Studio canvas and including termination circumstances. This final choice is essential: That is how an agent “is aware of” it has accomplished a activity and must ship outcomes to both a person or a calling perform. Brokers might 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 appropriate AI mannequin for an agent, maybe one which’s been fine-tuned or that gives multi-model actions so you’ll be able to work with photos and audio in addition to textual content prompts. Nodes in a group might be edited so as to add parameters the place essential.
Below the hood, AutoGen is a declarative agent improvement setting, with JSON description of the assorted parts that go into making an agent. You possibly can swap 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 affords a gallery the place brokers and different elements might be shared with different customers. When you’ve constructed an agent, you’ll be able to consider it inside Studio’s playground earlier than constructing it into a bigger course of.
Utilizing declarative programming strategies to construct agent groups is sensible; usually the data wanted to assemble parts 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 parts of these processes, who higher to design these duties than the individuals who know precisely what must be finished?
There’s lots but to return for Semantic Kernel in 2025. Now that we’re popping out of the experimental section of enterprise AI the place we used chatbots to learn 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 kind the spine of our companies. Semantic Kernel is beginning to step out into the enterprise IT world. It’ll be attention-grabbing to observe the way it and AutoGen make the most of the talents and data that exist throughout our organizations, past IT and improvement groups.