A marionette-lighting advisor has two implementations. One camp wants to know which scores better on agreed metrics. The other wants a pseudo-oracle that hunts disagreements as defects. How should those jobs be assigned?
Select an answer to reveal the explanation.
Short Explanation
Which implementation scores better on agreed metrics is A/B testing. A pseudo-oracle that hunts disagreements as defects is back-to-back testing. Swap those jobs and the contrast is gone. Neither job is static drift testing of lighting-feature shapes, and neither is a documentation review of a missing hardware note.
Full Explanation
A/B decides which variant is better via metrics and statistics. Back-to-back hunts disagreements as defects. Swapping those jobs, or renaming both as drift testing or card review, misses the contrast.