Building AI Assistants in Languages I Barely Knew
How I learned Go and Rust by building personal AI tools, made a lot of mistakes, and somehow ended up with working software.
BLOG.LOG
I Merged Five PRs in One Afternoon to Fix One Feature
Adding GitHub Copilot OAuth to joshbot took twenty minutes to implement and one very long day to actually make work. A story about hidden state, path bugs, and the debug log that finally explained everything.
I Made Silly Games and Learned Things
From chicken mobs to chopping vegetables at alarming speeds - my journey into making games that probably shouldn't exist.
Five Bugs That Hid in Plain Sight for Months
A canvas game, five production bugs, and what each one reveals about why certain failures are invisible to the person who wrote the code.
Rewriting a Portfolio Game in One Sitting (The Bugs Were Spectacular)
How a simple 'center the game' request turned into a complete rewrite, a canvas rendering bug I'd missed for months, and a lesson in agentic debugging.
I Gave Claude Code a Task and Told It Not to Ask Permission
What happens when you hand an agentic coding tool a real production codebase, say 'go until completion,' and actually mean it.
Building an Agentic SDLC Framework (Without Losing My Mind)
The chaotic, occasionally painful, and ultimately rewarding journey of building an AI-powered SDLC framework for regulated environments.
OpenCode: My Terminal-Based AI Coding Agent for Agentic Development
Why I'm moving my AI workflow to the terminal with OpenCode, a privacy-first, open-source coding agent.
A New Chapter
Rebuilding this space to share what I've learned about software engineering, system architecture, and leading with empathy.