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.
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.
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.
Build a cost-effective, private AI Agent solution on Google Cloud using Chainlit and Vertex AI. Detailed architecture and code guide.
Build a personal AI assistant using Google Cloud Run, Vertex AI, and Google Chat. A guide to architecting context-aware agents.
Speed up AI agent development on GCP with Ackgent. Build, deploy, and iterate faster using Google ADK and Agent Config's declarative approach.
Build custom AI image workflows fast with Combo-Banana. Empower designers to automate tedious editing tasks with Google Nano-Banana.
How I built GentWriter with Google's ADK: a multi-agent system that turns one article URL into an SEO description, an X post, and a LinkedIn post.
A Python notebook agent that reviews GitHub repositories against your own guidelines automatically, using Google Colab, the GitHub API, and Gemini models.
Video meetings on platforms like Google Meet are essential for collaboration, but how often do crucial details get lost moments after the call ends?
Team collaboration often lives and breathes within chat applications like Google Chat or Slack.
The MLOps Python Package is your go-to solution for building robust and reproducible AI/ML workflows. Check out the latest v4.1.0 release!
The AI landscape is constantly evolving, pushing the boundaries of what’s possible with technology.
The Cookiecutter MLOps Package offers a powerful code template to jumpstart your MLOps journey and accelerate your AI/ML development.
MLOps practitioners (rightfully) point out that running notebooks in production is a bad software practice, but what are the alternatives?