01 / Writing

Notes from the build.

Architecture, .NET, cloud, AI, and graph databases — written from production, not theory.

All .NET 28 AI 15 C# 12 Graph Databases 9 Architecture 8 NebulaGraph 8 ASP.NET Core 7 .Net Core 6 AI Agents 5 Postgresql 5 EF Core 4 MCP 4 Agentic Coding 3 Claude Code 3 Edge AI 3 Graph Database 3 IoT 3 Knowledge Graph 3 LLM 3 RAG 3 Semantic Kernel 3 Vector Search 3 nGQL 3 Agent Framework 2 Agent Memory 2 ArangoDB 2 Azure 2 Blazor 2 Claude 2 Developer Tools 2 OpenAI 2 Security 2 Semantic Search 2 Software Engineering 2 Tech 2 TimescaleDB 2 .Net Core Push Notification 1 AWS Deployment 1 AWS Lambda 1 Access Management 1 Agents 1 Agile 1 Anthropic 1 Arduino 1 Authentication 1 Benchmark 1 CDK 1 CORS 1 CQRS 1 Code Quality 1 Code Review 1 Context Engineering 1 Custom Claim 1 Data Engineering 1 Databases 1 ESP32 1 Embedded 1 Embeddings 1 EntraId 1 Function Calling 1 IAC 1 IBM MQ 1 Infrastructure as Code 1 JWT 1 MediatR 1 Message Queue 1 Microsoft.Extensions.AI 1 Multi-Agent 1 MySQL 1 Neo4j 1 Npgsql 1 Observability 1 OpenTelemetry 1 Postgres 1 Productivity 1 Raspberry Pi 1 Recommendation Systems 1 Remote Work 1 Research 1 Rust 1 Scrum 1 SignalR 1 Software Architecture 1 Team Leadership 1 Technical Debt 1 Testing 1 WebMCP 1 Windows Universal App 1 pgvector 1

Featured · October 29, 2026 · 7 min

Sharing State Across Sessions and Agents: Memory, MCP, and Handoffs in .NET

Agents forget everything between sessions and cannot see each other's work by default. This third part of Agentic Engineering for .NET Teams covers the practical patterns: persistent memory, MCP servers, multi agent coordination, and the C# wiring that makes them work together.

Read article

October 29, 2026 · 7 min

Context Engineering: Getting the Right Information to Your .NET Coding Agent

An AI coding agent is only as good as the context it sees. Context engineering, the discipline of deliberately curating what your agent reads, is the difference between an assistant that rewrites your service layer correctly and one that confidently breaks it.

Read

October 29, 2026 · 8 min

Claude Code for .NET Developers: A Practical Agentic Workflow

Claude Code is a terminal first AI agent that reads, edits and runs your .NET codebase on its own. Here is how to set it up, drive it well, and keep it safe in a team.

Read

October 23, 2026 · 8 min

Function Calling in C#: Building Tools Your AI Agent Can Call

Function calling turns a chatbot into an agent. A working C# agent loop with the official Anthropic SDK 13: tool definitions, parallel tool calls, structured errors, an EF Core dispatcher and the production concerns, all compiled and run.

Read

October 6, 2026 · 6 min

Keeping Your Knowledge Graph Current Without a Dedicated Team

A knowledge graph that nobody updates becomes a lie with good syntax. This article builds the automated maintenance loop — deriving edges from git history, deployment manifests, and OpenTelemetry service maps, reconciling on a schedule, and handling conflicts with provenance on every edge.

Read

October 6, 2026 · 7 min

Hybrid Retrieval in C#: Combining Vector Search, Graph Traversal, and Reranking for Agent Memory

Vector search finds candidate entry points; graph traversal expands context around them; a cross-encoder reranker decides what actually reaches the model. This article implements that full pipeline in C# with real token budgets, RRF fusion, and deduplication.

Read

October 5, 2026 · 6 min

Edge AI with .NET, Part 3: Vision OCR You Can Actually Trust

Reading utility meter digits with a vision model is a solved demo and an unsolved production problem. This article covers prompt design, image detail costs, the documented failure modes that matter, and the validation layer that makes a GPT-6-Astra reading safe to persist.

Read

October 5, 2026 · 7 min

Building an Agentic System in .NET, Part 6: Redaction, Audit and the Safety Layer

If you archive every agent session, you also archive every secret anyone ever pasted into one. This last part covers the full safety layer: redaction pipelines, audit trails, prompt injection threat modelling and retention pruning, with code.

Read

October 5, 2026 · 7 min

Building an Agentic System in .NET, Part 5: Designing an Agent Bus in ASP.NET Core

Design a production agent bus in ASP.NET Core 10 with EF Core, SignalR and PostgreSQL, covering agent registration, topic channels, at least once delivery, claim semantics with row level locking, and self contained hand off payloads.

Read

September 28, 2026 · 7 min

Building an Agentic System in .NET, Part 4: Keeping Memory True

Stale agent memory is not just wasteful, it causes real failures that are hard to trace. This part builds the whole defence: timestamps, decay scoring, deduplication, contradiction detection, verification on read, and scheduled pruning as .NET hosted services.

Read

September 23, 2026 · 7 min

Building an Agentic System in .NET, Part 3: Durable Memory with Postgres and pgvector

Give your .NET agent a long term memory it can actually recall. Model MemoryItem in EF Core, generate embeddings with Microsoft.Extensions.AI, store them in Postgres with pgvector, and build an HNSW cosine index with a ranked recall query that blends similarity, recency and importance.

Read

September 19, 2026 · 6 min

Building an Agentic System in .NET, Part 2: Writing an MCP Server in C#

How to expose your own tools to any AI agent by building a Model Context Protocol server in C# with the official ModelContextProtocol SDK v2.2.0. Tool design, input validation, context window budgeting, and the naming mistakes that make models misuse your tools silently.

Read

September 18, 2026 · 7 min

Building an Agentic System in .NET, Part 1: Anatomy of an Agent Harness

A chat wrapper is not an agent harness. This article walks through every structural component a real .NET 10 agent host needs, the turn loop, tool dispatch, persistence and the safety layer, and shows the minimal C# skeleton that survives a crash.

Read

February 6, 2026 · 9 min

From Graph Traversal to Semantic Discovery: Adding Vector Search and LLM Reasoning to Your ArangoDB .NET 10 API

In the previous article, I built a .NET 10 API […]

Read

October 20, 2025 · 16 min

Building a Retrieval-Augmented Generation (RAG) System in .NET

How we built a complete RAG pipeline in C#, from tokenization and ONNX embeddings to vector search in PostgreSQL with PgVector and local LLM inference with LLamaSharp. No Python anywhere.

Read