AI SCHEDULE REVIEW - TWO-RUN WORKSHEET - VERSION 1
Keep the exact fictional input and each original output separately.

Input version:
Run A date, tool and visible settings:
Run B date, tool and visible settings:
What changed between the two runs?

Mark each check: meets check / needs correction / could not test.
Case    Run A        Run B        Evidence or missing confirmation
SCH-01  ___________  ___________  ________________________________
SCH-02  ___________  ___________  ________________________________
SCH-03  ___________  ___________  ________________________________

Which instant, date, offset or duration needs a correction?
What must the organizer confirm before an invite is sent?
If the runs are not comparable, what baseline should be kept?
Next boundary case to check: