Guides
Guides: adding AI to your .NET applications
Reference pages rather than opinion pieces: what you need to know to add AI to an existing .NET and Microsoft estate, with the code, the decision tables and the sources. Every guide carries the date it was last revised.
Updated on 1 October 2026
Copilot or custom AI: a comparison for deciding, one process at a time
What Copilot actually reaches in October 2026 (connectors, agents, Copilot Studio), what stays out of its reach, what the licence costs and who answers for the result. One comparison table and five questions to decide.
Updated on 1 October 2026
AI in a French accounting firm: what to automate, in what order, under professional secrecy
Electronic invoicing has been taking data entry away from French accounting firms since 1 September 2026. What AI can take on next, the three levels of tools, what professional secrecy imposes on the architecture, and seven steps to start.
Updated on 1 October 2026
Integrating AI into an existing .NET application: the architecture guide
Four ways to wire AI into a .NET application already in production, where the code belongs, and the guardrails that hold: typed output, deterministic checks, tools under the user's identity, writes behind approval. Tested C# code on GitHub.
Updated on 1 October 2026
AI in a French mid-cap: where to start when you have an IT department, several entities and an ERP
58% of businesses in France with 250 or more employees report using AI in 2025. What sets an AI project in a mid-cap apart from one in an SME, the three levels of tools, the candidate processes, who decides what, and eight questions to settle before the first project.
Updated on 1 October 2026
What drives the cost of an AI project for an SME: cost items, levers and public benchmarks
A third of the businesses in France that use AI say its cost holds them back. The six cost items of a project, what running a model really costs, the seven levers that move a quote, and eight questions to judge it. No house rates: public benchmarks, dated and sourced.
Updated on 30 September 2026
Semantic Kernel or Microsoft Agent Framework: what to do with an existing .NET application
Agent Framework 1.0 shipped in April 2026 and Semantic Kernel has moved to maintenance. What changes in a .NET application, what stays put, the code before and after, and when to migrate.
Updated on 30 September 2026
RAG on SQL Server 2025: a reference architecture for an existing .NET application
Wiring RAG into a .NET and SQL Server application without a separate vector store: the VECTOR type, chunking that follows the documents, permissions enforced in the query, an Agent Framework agent. Complete, tested code on GitHub.