AI TEST PLAN REVIEW - TWO-RUN WORKSHEET - VERSION 1

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

For each ID, record meets check, needs correction, or could not test.
Keep both original plans and the criterion they address.

Case     Run A       Run B       Missing state, action or observation
TEST-01  __________  __________  ___________________________________
TEST-02  __________  __________  ___________________________________
TEST-03  __________  __________  ___________________________________

What failure could still pass the proposed test?
What evidence would a real run need to capture?