Measures

Time in app, opens, and cards viewed are diagnostics. Measure whether judgment improves and autonomy is earned:

• time to first material change;
• runtime handoff completion, time to readable first expert, and interrupted-activation resume success;
• percentage reaching a sourced Story and grounded Position without opening advanced configuration;
• decisions completed without rubber-stamping or later reversal;
• Positions re-priced on evidence with a legible track of how the read moved;
• corrections reflected in later behaviour;
• autonomy expanded without surprise or rollback;
• month-six tutoring, return, and export.
• manual export/share requests and retained creator supply before Marketplace investment.

The strongest qualitative test is: What does this expert do differently because you taught it?