You don't trust the agent; you trust the action
Why assigning trust by action, not by agent, is the design system work nobody's doing yet
Why assigning trust by action, not by agent, is the design system work nobody's doing yet
How the graph keeps going up anyway
You've taught agents your design system. You still don't know whether they're following it.
Authored change has outpaced the review model, and that breaks more than it looks.
And whether the next generation of practitioners will get the same thing.
Reopening every decision you left implicit, and settling it without you
The practices exist. The discipline hasn't caught up
AGENTS.md, SKILL.md, DESIGN.md, and where each one fits
How the promises your system makes became the thing agents read first.