Notes that became tools.
A developer's notebook on second brains, AI agents, and build-in-public. Sometimes the writing finds a shape and becomes a thing you can buy. StackMind was the first.
Your coding agent is too agreeable
A Stanford/CMU paper measured a 47% endorsement gap between AI and humans on personal advice. The same RLHF mechanism applies to coding agents — and explains why your default reviewer subagent is structurally too kind. The operational answer is harness, not prompt.
The LLM Wiki — Notes that maintain themselves
The reason every notes system becomes a graveyard is maintenance cost. LLMs don't have that cost. Here's what changes when the model does the filing.
What Opus 4.7 actually changes in your workflow
A 'direct upgrade' that asks you to re-tune your prompts is not a direct upgrade. The two changes that break your existing work, the four that don't, and the one they buried that matters most.
Why the PARA method doesn't work for developers
PARA was built for knowledge workers, not developers. The four categories collapse the moment you try to file a bug fix, an AI conversation, or a tech decision.
How to build a developer knowledge base that actually works
Most developer note systems fail because they're organized by when you wrote something, not by when you'll need it. Here's how to build one that compounds.
The notes a developer keeps so the work compounds
On knowledge that builds on itself, why most of yours doesn't, and what changes when it does.
StackMind
Nine connected Notion databases for the bugs, AI conversations, and tech decisions developers keep losing. Built because I was tired of fixing the same CORS error twice.
StackBench is a developer's writing and tools, kept in public. No name, no photo — just the work. About.