Blog
All the articles posted so far...
The Implicit Signals Your Cloud Agent Is Reading
The prompt is only one input. The cloud agent also reads your issue structure, your git hooks, your hook decisions, and your environment variables — most of it silently, and not always the way you'd expect.
The Loop Doesn't Close Itself
GitHub Copilot finishes and leaves the PR in draft. Here's the 4-agent scored dev loop, CI gate hooks, and setup-step investment I built around it to make that actually mean something.
GitHub Cloud Agents Work When You Build the Feedback Loop
After 3-4 days of bad PRs, I learned the hard part of using a GitHub Cloud Agent isn't the prompt — it's the environment, hooks, and validation layers that tell the agent whether it actually succeeded.
Running to Stand Still: What Playa del Carmen Taught Me About Real Rest
On burnout signals, the habit of turning vacations into projects, and what three days at a friend's wedding in Mexico taught me about actually stopping.
How I Turned My Obsidian Vault Into a Queryable Second Brain
The problem with notes that hold knowledge but fail at retrieval, and the local-first RAG system I built to fix it.
Why I Treat Challenges as Feedback Loops, Not Failures
How shifting from failure-labeling to feedback extraction transformed my approach to engineering challenges, creating sustainable growth through structured retrospectives and concrete improvements.