Enterprise SDK for .NET/Java/Python; skills and planners under Microsoft/Azure governance. Architecture: Skills (plugins) + planners; multi-language (C#, Java, Python). Merged with AutoGen into the Microsoft Agent Framework (GA since April 2026); Semantic Kernel is in maintenance mode. Best suited: Enterprise copilots in .NET/Azure with governance and multi-…
Use this profile to understand the building block briefly, place it in the model, and switch to the 360° assessment when needed.
Technical building block: can be automated, integrated, or operated.
Concrete cog in the system that works inside larger relationships.
Semantic Kernel is an open-source SDK from Microsoft that connects AI models with functions, data, and business logic to build application-specific agents and workflows.
Microsoft released Semantic Kernel as an open-source project in 2023. It was created as an SDK for orchestrating large language models with existing programming languages, plugins, and enterprise capabilities, emphasizing application integration.
The model produces text or decisions, while the kernel controls which tools and context are available. Plugins package functions, prompts, and native code; the host application must constrain and observe planning, permissions, data access, and execution.
Packages functions and descriptions that a model can use.
Application layer connecting model calls, functions, context, and execution.
Coordinates multiple model and function steps into a workflow.
Semantic Kernel matters when AI capabilities need controlled integration into existing .NET, Python, or Java applications. Reliability requires clear tool contracts, permissions, observability, tests, and safeguards against unintended actions.
Where this building block is located in the topic model.
No structure path available.
Explore how this building block connects to concepts, methods, technologies, and tools.
These sources establish the term and its professional meaning.
All direct connections of the current building block in a compact text view.
This classification shows where the building block typically matters, how demanding it is, and what kind of impact it has in the model.
The level within the organization (enterprise, domain, team) at which the AssetBlock is applied.