A clock-tower chime predictor was swapped overnight. Four desks report four different pains: the kiosk dies on first request; the live hit-rate is worse; the new model disagrees with last week’s on the same rows; last winter’s accepted layouts now fail. How should those four update risks be matched?

Four desks, four pains after an overnight swap: the kiosk dies on first request (smoke), the live hit-rate is worse (A/B), the new model disagrees with last week’s on the same rows (back-to-back), and last winter’s accepted layouts now fail (regression). Collapsing all four into smoke, Chapter 7 canaries, or documentation reviews misses those four update risks.