Topic
AI on .NET
Most of the enterprises we work with run on .NET, with Azure underneath. These notes cover building agents in C# on Microsoft Agent Framework, and where the .NET tooling, including for MCP servers, still has gaps.
Microsoft Agent Framework gives a .NET team the agent loop, tool calling and structured outputs without leaving C#, and the tools an agent calls are strongly typed methods with schemas generated from the types. We built two agent systems on it between 2024 and 2025: DevGuardian AI, a multi-agent system of three role-based review agents with a Blazor interface, and MayAI, one agent with six tools behind a SvelteKit app. Azure OpenAI and OpenAI-compatible endpoints through OpenRouter worked behind the same abstraction, so MayAI could switch models without touching the agent.
Server-side grounding came out of MayAI and is now the pattern we use in every agent that puts real items in front of a person. The gap, as of October 2026, is tooling: the C# SDK for the Model Context Protocol is a first-tier SDK, yet no .NET-native tool inspects, tests or load tests an MCP server. The service behind these notes is AI agents and multi-agent systems.
October 8, 2026 · 4 min read
Keeping AI agents honest: the server-side grounding pattern
Server-side grounding is a pattern in which an AI agent returns only identifiers and the server builds everything the user sees from real tool results, so the agent cannot show an invented item. How we built it for MayAI, the six rules around it, and where it applies.
October 8, 2026 · 4 min read
Multi-agent systems in .NET: what we learned building two of them
A multi-agent system is one in which several AI agents, each with its own role and tools, work on the same task. Seven lessons from building two agent systems on Microsoft Agent Framework in .NET: DevGuardian AI, with three review agents, and MayAI, with one agent and six tools.
Working on one of these problems?
The patterns in these notes are the ones we use on client work. Tell us what you are building.
Book an AI consultation