I Was Wrong About MCPs
In June I wrote about replacing MCPs with skills and scripts, and about a skill file beating an MCP server almost everywhere except where there’s no CLI. I …
Read →AI Development
Practical guides and opinions on building with AI — workflows, tools, and what I'm noticing along the way.
8 posts in this category.
Agent to Agent Communication: MCP Is the Wrong Layer
A few weeks ago I wrote about replacing MCPs with skills and scripts. Someone pushed back in the comments over on LinkedIn with one exception: agent to agent …
Read →I Stopped Using MCPs and Replaced Them with Skills and Scripts
Update, October 2026: I’ve changed my mind about part of this post. Here’s why. Everyone’s excited about MCPs. The Model Context Protocol is supposed to be the …
Read →grug make AI skill. grug happy.
grug been thinking about complexity demon lately. complexity demon sneaky. complexity demon hide in code review. complexity demon whisper “just add one more …
Read →The Testing Pyramid Still Matters (Even When AI Wrote Your Tests)
I’ve been spending a lot of time in agentic AI workflows lately. Describe a feature, the agent writes the code, the tests, and the PR. It’s genuinely …
Read →AI and the Human Factor - My Observations
Over the last year, I’ve been watching how people use AI coding tools. GitHub Copilot, ChatGPT, Claude - everyone’s got access to them now. But the results? …
Read →Building Interactive MCP Tools with Elicitations: A Practical Guide
The Model Context Protocol (MCP) is revolutionising how we build AI tools, but a powerful new features recently added to the protocol will be a game changer: …
Read →How I Built Interactive AI-Powered Training with GitHub Copilot
One of my current projects is a migration from Azure DevOps to GitHub Actions. I saw a challenge: how to effectively train DevOps teams on new tools in an …
Read →