[ Tech stack ]
Microsoft Semantic Kernel
Microsoft's open-source SDK for integrating LLMs into .NET, Python and Java applications.
Semantic Kernel is Microsoft's open-source SDK for orchestrating language models inside existing code: the kernel loads plugins (native functions or prompts), exposes them to the model through automatic function calling, and manages connectors (Azure OpenAI, OpenAI, Hugging Face, Ollama) and vector stores. Its agent framework adds conversational agents, filters and OpenTelemetry telemetry. It's our choice when a .NET or Azure IT department wants to industrialize generative AI under its own security and observability standards.
[ Why Microsoft Semantic Kernel at Dexon ]
What this technology does well, and why we use it.
Typical usage: Business copilots on Azure, internal process automation, assistants embedded in .NET applications.
- 01
C#, Python and Java SDKs: AI inside existing business code.
- 02
Plugins and automatic function calling: the model invokes your functions.
- 03
Connectors for Azure OpenAI, OpenAI, Hugging Face, Ollama and vector stores.
- 04
Filters, OpenTelemetry telemetry and Microsoft backing: ready for the enterprise.
[ Complementary technologies ]
The building blocks we often mobilise alongside.
A stack rarely exists alone. Here are the technologies Dexon most often pairs with this one, through pipeline habits, usage similarity or internal mastery. Click on a building block to see its scope.
[ Reassurance ]
- 0+
- custom projects delivered
- 30
- engineers, designers, project managers
- 80 %
- from top French schools
- 24 h
- average reply time
[ They trust us ]
More than 100 French and European companies trust us
[ Press ]
They talk about us.
Nationwide coverage by BFM Business, Le Figaro, Challenges, La Tribune and CNews. An outside reading of our work and our innovations.
