AGENTS.md speaks UNIX, and you should too
Unix gives coding agents the tools. AGENTS.md explains where to edit, how to check, and what to preserve. Lessons from my dotfiles and human review.
- Agent
- Coding
- Project
With your consent, Google Analytics measures which pages help visitors so I can improve them.
Nothing loads before you accept, and you can change your choice from the footer at any time. Privacy
Writing
Pragmatic field notes on AI agents, MLOps, cloud architecture, and engineering systems.
Get new articles in your feed reader. Copy the RSS link into your reader to subscribe.
Unix gives coding agents the tools. AGENTS.md explains where to edit, how to check, and what to preserve. Lessons from my dotfiles and human review.
AI coding agents amplify repository friction. How we redesigned an MLOps codebase around deterministic single-command gates, SQLite isolation, and AGENTS.md.
Agent-evolutions is a set of Agent Skills that turns a coding agent into a budgeted genetic search over a design space, with verifiable scoring at every step.
A coding agent is only as useful as the spec you give it. That sentence sounds like a truism until you watch it play out for an afternoon.
Pair-program with a coding agent for an afternoon and you start noticing a quiet, recurring tax.
Supagents compiles one Markdown persona per subagent into the native formats of Claude Code, Gemini CLI, GitHub Copilot, Cursor, OpenCode, and Kilo Code.
AI Coding — or Spec-Driven Development — is a recent trend that amazes as much as it scares IT engineers.
How I revamped my portfolio website, fmind.dev, in five nights using AI agents: preparing the agent, steering it, the result, and my key takeaways.
Bridge the gap between engineering specs and AI agents using Agent Skills. Learn to inject ‘Senior Engineer’ context for production MLOps.
A Python notebook agent that reviews GitHub repositories against your own guidelines automatically, using Google Colab, the GitHub API, and Gemini models.