.NET, Azure & AI Engineering Articles

RAG with EF Core and pgvector

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

Dynamic Agent Context with AIContextProvider

Series Deep Dive: Microsoft Agent Framework Part 6 of 19

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

Controlling Token Growth with Chat Reducers

Series Deep Dive: Microsoft Agent Framework Part 5 of 19

How to control token growth in Microsoft Agent Framework with message-count and summarizing chat reducers, including setup, tradeoffs, and when each approach fits.

State Management and Chat History

Series Deep Dive: Microsoft Agent Framework Part 4 of 19

How to manage short-term and persistent conversation state in Microsoft Agent Framework using AgentSession, StateBag, and a custom ChatHistoryProvider.

Use the Aspire Dashboard Standalone

Stop setting up complex observability stacks for local dev. Learn how to run the Aspire Dashboard as a standalone, lightweight OTLP viewer for any language.

Chat vs. Streaming: Don't Keep Your Users Waiting

Series Deep Dive: Microsoft Agent Framework Part 3 of 19

When to use RunAsync vs. RunStreamingAsync in Microsoft Agent Framework, and why streaming improves chat UX while blocking calls still fit structured outputs and background work.

Zero to First Agent

Series Deep Dive: Microsoft Agent Framework Part 2 of 19

How to initialize the Microsoft Agent Framework, connect to Azure, OpenAI or local Ollama models and execute your first asynchronous agent run.

Microsoft Agent Framework: Introduction

Series Deep Dive: Microsoft Agent Framework Part 1 of 19

How Microsoft Agent Framework builds on Microsoft.Extensions.AI, when it supersedes Semantic Kernel for new .NET agent systems, and where MCP, context providers, and workflows fit.

Context Compression in .NET

Reduce token cost and latency in .NET by compressing RAG context with a cheap summarizer model or an IChatClient middleware pipeline.

Stop Guessing – Use Golden Datasets for Prompt Evals

Use a small golden dataset to catch prompt regressions, compare changes against a baseline, and validate model updates before users do.