The blog
3 posts on AI engineering, internal tools and shipping in ambiguity.
#AI#Claude#AI agents#ambition#self-efficacy#FinOps Terminal
The model is no longer the bottleneck. We are.
Felix Rieseberg, at Anthropic, lays out a method for being more ambitious with models: altitude, depth, range. I break it down, test it against the studies that push back on it, and try it on FinOps Terminal, a project built in four days.
Featured #DevOps#Kubernetes#GitOps#FluxCD#git#terminal#Tauri#React
Cosmos Corp: an RPG for learning DevOps by actually doing the job
I built a desktop RPG where you learn the terminal, git, Kubernetes and GitOps by actually doing the job, on real containers, with a mentor named Sage.
Featured #AI agents#MCP#CLI#OpenAPI#spec2cli#Claude Code
Give your AI agents a CLI, not an MCP server
Why a CLI generated from an OpenAPI spec costs less context than an MCP server, what Claude Code changed in 2026, and spec2cli, a small open source tool that turns any API into a CLI.