01 / Writing

Notes from the build.

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

All.NET 20AI 11C# 9Architecture 7Graph Databases 7.Net Core 6ASP.NET Core 6NebulaGraph 5Postgresql 4EF Core 3Edge AI 3IoT 3Knowledge Graph 3MCP 3RAG 3Semantic Kernel 3nGQL 3AI Agents 2Agent Framework 2Agent Memory 2ArangoDB 2Azure 2Blazor 2Graph Database 2LLM 2OpenAI 2Security 2Semantic Search 2Tech 2TimescaleDB 2Vector Search 2.Net Core Push Notification 1AWS Deployment 1AWS Lambda 1Access Management 1Agents 1Agile 1Arduino 1Authentication 1CDK 1CORS 1CQRS 1Custom Claim 1ESP32 1Embedded 1Embeddings 1EntraId 1IAC 1IBM MQ 1Infrastructure as Code 1JWT 1MediatR 1Message Queue 1Microsoft.Extensions.AI 1Neo4j 1Observability 1OpenTelemetry 1Postgres 1Raspberry Pi 1Recommendation Systems 1Remote Work 1Research 1Rust 1Scrum 1SignalR 1Software Engineering 1Team Leadership 1WebMCP 1Windows Universal App 1pgvector 1

Featured · October 16, 2026 · 16 min

Why Agents Need a Knowledge Base: The Gaps an LLM Can't Fill by Itself

A model knows only what was in its training data, up to its cutoff, and very little about specialised fields or your own systems. Here are the four gaps a knowledge base fills in an agentic system, why a 1M token context window doesn't close them, and how to expose one to an agent in C#.

Read article