Stop Being the Loop
The shift from prompting AI to engineering loops — and what it means for our team.
Read →Writing
Thoughts on architecture, engineering, and building real things — often with AI in the loop.
The shift from prompting AI to engineering loops — and what it means for our team.
Read →Give agents a way to check their own work, run several in parallel, and let them loop in the background — the way the Claude Code team works internally.
Read →Stop paying tokens to re-read the same files every session. Graphify builds a one-time knowledge graph your AI assistant queries instead of grepping — fewer reads, faster answers, lower token bills.
Read →Cheap, unlimited AI is winding down, and the craft is maturing from prompt to context to harness engineering. The value now is in better scaffolding, not more tokens.
Read →AI made writing code trivial — which is why a tangled, undesigned codebase is now the most expensive thing you can own. Matt Pocock's case for why design, not prompting, is still the job.
Read →Stop stashing every time a PR review or prod hotfix interrupts your flow. git worktree checks out multiple branches at once, each in its own folder, all backed by one repo — no re-index, no waiting.
Read →AI generates plausible code fast — but plausible isn't correct. Why critical thinking is the core developer skill, and why AI makes it matter more, not less.
Read →AI crushed the cost of writing code — not the cost of understanding a problem. Why we're entering an era of personal, disposable software, and why lasting systems still need real engineering.
Read →An LLM can't own your system's architecture — only you can. LLMs are excellent executors, not architects. Think first, decide the design explicitly, and use the model to execute, explore, and explain.
Read →Known vulnerabilities in your dependencies can expose your app to real harm. How to run npm audit, read the report, fix what's fixable, handle the rest by hand, and gate CI on high and critical issues.
Read →