Last updated: 28 July 2026 I’ve been building out an AI agent, Iron Mind AI, a personal trainer agent, incrementally using the Microsoft Agent Framework. Each […]
AI-assisted engineering is easy to measure badly and the usual numbers appear first: active users, accepted completions, generated lines of code, tokens consumed, agent sessions and […]
Last updated: 28 July 2026 Retrieval-Augmented Generation is a pattern, not a framework, and the gap between a RAG tutorial and a RAG pipeline that stays […]
I have created a broader Draw.io MCP Diagramming Agent Skill for generating clear, structured and editable diagrams across a range of use cases, including cloud architecture, […]
Agent skills are a practical way to capture reusable engineering judgement for AI coding agents, whether that judgement relates to reviewing Terraform, creating architecture diagrams, writing […]
I’ve been using Claude Code heavily across AI engineering work: RAG pipelines, .NET MCP servers, content automation, agentic workflows. The way I use it now looks […]
A , , custom instruction file, or MCP configuration can affect how an agent reads a repository, calls tools, writes code, updates infrastructure, or explains a […]
The previous post made the case that AI-assisted engineering is becoming a platform concern. This post is about the follow-up question: what controls actually make that […]
I recently had a situation where a continuous Azure WebJob running a documentation crawler stopped overnight. The crawler formed part of an ingestion sequence in a […]
In this blog, I run through a debug session that took me a while to diagnose. Documents in a production RAG pipeline were intermittently failing to […]