Is your site agent-ready? Here's what I did to find out
The web has had two audiences for thirty years — humans and search bots. AI agents are a third, and most sites are not ready for them. Here is what I found when I actually tested mine.
Agentic engineering: the grown-up version of vibe coding
Vibe coding is a fine on-ramp, but at some point the lack of structure catches up with you. Agentic engineering is what happens when you apply proper engineering discipline to AI-assisted development — and it starts with specification, evaluation, and testing.
Five levers in Claude Code: a practical guide to CLAUDE.md, skills, hooks, MCP, and sub-agents
Claude Code ships with a rich set of extensibility features, and most developers are using maybe one or two of them. Here is a practical mental model for when to reach for CLAUDE.md, skills, hooks, MCP, and sub-agents.
Claude Code – The terminal assistant that actually gets it
For a long time, I have been a bit of a skeptic when it came to AI coding assistants. While they provided a convenient mix of Google-searching and autocomplete, they also made frequent mistakes and required a lot of guidance. But lately, I have been using Claude Code, and it feels like a bit of a gamechanger for how we interact with our codebases.
Azure identity - managed identities and roles
For a while I have actually not had to do much configuration of app registrations, managed identities and so on, simply because I often join teams who have other people doing that part. So it has been fun and at time challenging to get back into it, as I have had to lately. So to...