↓ Skip to main content

ai

this series is where i document how i use ai as a real work system, not as a novelty tool.

i write these posts to make decision quality visible: when ai is helping, when it is creating hidden cost, and which workflow choices keep outcomes stable over time. the goal is to make ai usage more deliberate, measurable, and easier to hand off across sessions.

you will see both operational playbooks and reflective pieces here. i care about execution speed, but i care just as much about clarity, cognitive load, and long-term maintainability.

the guardrails i actually use with ai agents

in ai liberty i argued that capable models take more liberties and need robust guardrails, but i did not show them. this is the concrete kit i actually use to keep speed without losing control, namely read-only and ask modes, command allowlists, scoped database credentials, branch protection, and human-in-the-loop gates for the few actions that are genuinely hard to undo.