Fifty chapters drafted in hours instead of the decade it would have taken by hand — and the Claude Code plugin that kept the manuscript from drifting as it scaled.
I spent the early 2000s shaving cycles off inner loops. Twenty years later I watch teams do the same thing with LLM tokens — and miss the actual ROI question.
Most platforms rot because they were built for a future that never arrived. Here's the heuristic I use to stay loose without going vague.
The quiet discipline of knowing when it's enough, and when it isn't.
Most teams don't have a technology problem — they have a decision-making problem dressed up as one.
The stack I reach for when I need to ship something small, boring, and reliable.
How I caught myself architecting around a rule nobody had ever made.
Cadence, agenda, attendees — these are UI choices. Treat them like one.
