How to host a Microsoft Agent Framework agent in Foundry while keeping authorization, conversation ownership, identity, and governance boundaries explicit.
How to decide when a .NET AI request should stay synchronous, stream its response, or move to a durable background job with HTTP 202 and a status resource.
How to test Microsoft Agent Framework applications with fake model clients, tool contract tests, structured output tests, routing tests, workflow tests, and eval-style regression checks.
How to use the Bogus library to generate realistic, repeatable, and domain-shaped test data in .NET, including faker rules, related objects, seeds, and practical boundaries.
How to make Microsoft Agent Framework behavior visible in production with OpenTelemetry traces, token usage, model calls, tool calls, Aspire local debugging, and Application Insights monitoring.
A quick tip for embedding Python directly into a .NET app with CSnakes when you want a small slice of the Python ecosystem without a separate API service.
How to expose Microsoft Agent Framework agents through AG-UI so frontends can handle streaming text, tool progress, approval requests, and shared state.
A quick .NET 10 tip for running a single C# file without creating a project, with package directives, argument passing, conversion, and preview multi-file support.
How to implement human-in-the-loop approval flows in Microsoft Agent Framework for risky tool calls, side effects, workflow state, and resumable review.
How to take an existing ASP.NET Core MCP server built with the official .NET SDK and run it on Azure Functions as a self-hosted custom handler.