On the coronary heart of Microsoft’s AI software 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) purposes, 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 purposes. That announcement fashioned the premise of Semantic Kernel’s 2025 street 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 basic availability. It will guarantee a steady, supported set of instruments able to ship production-grade enterprise AI purposes. The Agent Framework will kind the premise of Semantic Kernel’s deliberate integration with Microsoft Analysis’s AutoGen, together with the discharge of a standard runtime for brokers that’s constructed utilizing each platforms.

The Agent Framework is meant to assist construct purposes round agent-like patterns, providing a manner so as to add autonomy to purposes and to ship what Microsoft calls “goal-oriented purposes.” This can be a good definition of what trendy agentic AI needs to be: a manner of utilizing AI instruments to assemble and handle a workflow based mostly on a person request. It then permits a number of brokers to collaborate, sharing information and managing what may be considered lengthy transactions that work throughout many various software 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 quite than direct human actions (and so as to add human approval steps as a part of a dynamic workflow). This allows you to give attention to 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.

Constructing a Semantic Kernel agent requires an Agent class earlier than utilizing an Agent Chat to help interactions between your agent workflow and the AI and API endpoints used to finish the present activity. If a number of brokers have to be known as, you should use an Agent Group Chat to handle these inside prompts through the use of 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 in a position to construct on current Semantic Kernel methods, too. For instance, brokers can use current or new plug-ins in addition to name features. Working with exterior purposes 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 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 establishing queries by parsing person inputs.

No-code agent improvement 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 software frameworks corresponding 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. Nevertheless, a step can include an agent if it has well-defined inputs and outputs. Processes can make the most of frequent patterns, and there’s no motive to have features 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 comparable approaches to working in event-driven environments. This is a crucial basis, as Orleans’ transfer from being a Microsoft Analysis mission 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 help for multi-agent operations in Semantic Kernel. Because it’s been a analysis mission, there’s nonetheless some work essential to deliver the 2 platforms collectively, with AutoGen supporting each .NET and Python, very similar to Semantic Kernel.

Actually AutoGen simplifies the method of constructing brokers, with a no-code GUI and help for a wide range of completely different LLMs corresponding to OpenAI (and Azure OpenAI). There’s additionally help 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 software and a mannequin shopper. As soon as put in, you possibly can construct a easy agent with a handful of strains of code. Issues get attention-grabbing once you construct a multi-agent software or, as AutoGen calls it, a staff. Groups are introduced collectively in a gaggle chat the place customers give brokers duties. It comes with prebuilt brokers that can be utilized as constructing blocks, corresponding to a person proxy, an online surfer, or an assistant.

You may rapidly add your individual extensions to customise actions inside 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 rapidly construct brokers utilizing prebuilt parts and your individual code, in addition to instruments for dealing with directions and prompts. Lastly, the Extensions API is the place you possibly can add help for each new LLMs and your individual code.

A lot of the documentation focuses on Python. Though there’s a .NET implementation of AutoGen, it’s lacking documentation for key options corresponding to AgentChat. Even so, .NET is probably going one of the best software to construct brokers that run throughout distributed techniques, utilizing its help for .NET Aspire and, via that, frameworks like Dapr.

Constructing multi-agent groups in AutoGen Studio

AutoGen Studio is maybe essentially the most attention-grabbing half and would work nicely as a part of the Semantic Kernel Visible Studio Code extension. It installs as a neighborhood net software and offers a spot to assemble groups of brokers and extensions, with the goal of establishing a multi-agent software while not having to jot down any further code (although you should use it to edit generated-configuration JSON). It builds on prime of AutoGen’s AgentChat service.

Functions are constructed by dragging parts onto the Studio canvas and including termination circumstances. This final choice is necessary: That is how an agent “is aware of” it has accomplished a activity and must ship outcomes to both a person or a calling operate. Brokers may be additional configured by including fashions and extensions, for instance, utilizing an extension to ship a RAG question in opposition to enterprise information. A number of mannequin help helps you select an appropriate AI mannequin for an agent, maybe one which’s been fine-tuned or that provides multi-model actions so you possibly can work with photos and audio in addition to textual content prompts. Nodes in a staff may be edited so as to add parameters the place essential.

Below the hood, AutoGen is a declarative agent improvement atmosphere, with JSON description of the assorted components that go into making an agent. You may swap to a JSON view to make modifications and even convert AutoGen AgentChat Python to JSON and edit it in Studio. To simplify constructing new purposes, it provides 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 methods to construct agent groups is sensible; typically 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 lots 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 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.