There is a familiar first half-hour to a new engagement. You arrive at a cluster or VM with a problem to investigate, then start reconstructing the same diagnostic commands you used last week: kube...

Can a local-first coding agent help with infrastructure work without becoming an unattended deployment system? This milestone defines small, repeatable Terraform and platform-engineering tasks, the...

What does a reproducible local LLM environment for Terraform work look like when it is designed not to become an accidental deployment system? For this series, it is a version-pinned local runtime...

Can a local model help with Terraform and platform-engineering work without turning an experiment into an unsafe infrastructure deployment path? That is the question for this series. It is not an ...

🤖 AI co-author: GitHub Copilot An idea used to need a fair amount of ceremony before it became software. Someone needed enough uninterrupted time to make a start. A team needed enough shared cont...

🤖 AI co-author: GitHub Copilot Google’s recent article, Why Go is an ideal language for AI-assisted software engineering, makes a useful argument: as agents produce more code, our bottleneck move...

There is a slightly strange gap in the current agentic-coding conversation. We are getting very good at talking about prompts, models, context windows, skills, MCP servers, and whether an agent sh...

I saw a photo of an SF billboard with what looked like a broken URL: https:// {64659, 123310, 75584, 8138, 38271} It led to Listen Labs’ Berghain Challenge, where you act as a nightclub bouncer an...

I have written before about publishing my own collection of agent skills through npm. At the time, the appealing bit was the small command: npx skills install @abuxton/skills Put a useful SKILL....

I owe you an apology for the quiet August. I have not posted much because personal life took priority: I got married. It was a very good reason to step away, but it is still nice to be writing agai...