The Practice, Graded
Gauges Green grades the practice in public because the harness is supposed to improve work, not just remember it. Each mature scorecard has an append-only history, evidence per regrade, and a visible explanation of what moved.
Engineering is live first because the harness itself is the foundation. Client-work, marketing, and function-specific partner scorecards will appear here when they have enough history to be useful rather than performative.
The lowest engineering line is usually output quality. That grade measures whether the harness produces useful work without Ryan having to restate context, correct invented facts, or clean up noisy briefs. It matters because the harness is only valuable when it raises output quality while reducing operator load.
A scorecard is useful only if it changes behavior. For clients, the important question is simple: does the harness reduce the amount of context Ryan has to restate, keep unsupported claims out of important work, and make follow-through visible before commitments disappear into memory?