Writing archive
Field notes from building with AI.
Essays about product engineering, agents, work, and the awkward gap between a promising idea and a useful thing.
All posts (29)
The right model, not the best model
Test the model on your work before paying more.
Waiting for cheap AI to end
Today's losses don't settle tomorrow's AI prices.
Don't ask stakeholders what they want. Make them click something
A prototype's job isn't to look finished - it's to give people something to disagree on
One year later, I write for myself first
The thinking matters more than the finished article.
Stop treating shipped specs as documentation
Specs guide the build, then become history.
I am building five iOS apps before I market them
I am recording a five-app bet from day zero.
Five Bets #1
My first public skill - and the part it can't hand you
The one command installs the prompt. Not the work.
Hand on the Wheel #2
I don't read most of the code my agents write
I read the critical code, skim the rest, and never hand off the architecture.
Hand on the Wheel #1I gave my blog a Markdown twin for agents
Same URL, 80% fewer tokens. No server.
I was regenerating Claude's answers just to copy them
There was a slash command for that.
LLMs are shortsighted and that's your fault
They optimize for now. You're supposed to know what comes next.
I built a statusline because /usage is a distraction
Stop interrupting yourself to check how much you have left.
The leaked code isn't the story. The response is.
Blame the process, not the person.
I wiped my Mac and forgot to install Cursor
From must-have to afterthought in under a year.
The code your AI writes is untrusted. You run it anyway.
AI-generated code is untrusted by definition. So why are we running it with full access to our credentials, filesystems, and production databases?
Your AI setup is premature optimization
You already know the rule. You're just not following it.
Not knowing how to code is not a superpower
It's a ceiling.
Code review is becoming a fiction
LGTM is not a review strategy.
Most of your AGENTS.md is wasted tokens
4% better. Or worse. Depends what you write.
Chasing models won't make you better at using them
Skill the model, not the benchmark
Stop buying courses. Start asking questions
Why mass-purchasing courses failed me and how conversations with AI taught me more about backend development than any Udemy sale ever could.
2025: The year I stopped yapping and started shipping
Why I'm just a 'decent' developer (and that's perfect for AI)
Ego kills AI adoption faster than bad code
AI hype cycle: Wright brothers edition
Flying jets, building runways
AI will write 90% of code. Here's why that doesn't scare me
It's not replacing us
We're all getting hooked on cheap AI
$20 monthly, $140 worth of compute
Trading my developer comfort zone for real business skills
When building meets reality
I thought I was behind, turns out I'm just specialized
Different experience, not missing experience
Hello, I'm building
Frontend dev turned product builder