Ai-Engineering

When to use Microsoft Agent Framework workflows for explicit, observable, resumable, long-running orchestration, and why normal C# code is often the better choice.

How to delegate work between Microsoft Agent Framework agents by exposing focused agents as function tools, and when this is better than manual routing or a workflow engine.

Why CancellationToken matters more in .NET AI systems, and how to pass it through LLM calls, streaming responses, embeddings, retrieval, and tool execution.

Why AI systems should be designed not only around model context windows, but also around the human capacity for judgment.

How to route requests between specialized Microsoft Agent Framework agents with a cheap intent agent, structured output, and a normal C# switch statement.

How to extend Microsoft Agent Framework agents with MCP tools and Agent Skills, when to use each model, and what trust boundaries to keep around external servers, local files, and scripts.

Use structured output in Microsoft Agent Framework to turn LLM responses into typed C# objects that can be validated, tested, and used safely in application code.

How to expose small C# methods as Microsoft Agent Framework tools, pass application services through dependency injection, and protect side-effecting actions.

How to build RAG retrieval in .NET by storing embeddings in PostgreSQL with pgvector and querying them through EF Core.

How to use AIContextProvider in Microsoft Agent Framework to inject dynamic memory, reduce tool-token overhead, add guardrails, and extend agent context at runtime.