Your question is Debug Consistently Inaccurate Predictions. Take a moment with it on the right.
Talk me through your thinking if you like. When you're confident, submit your answer and I'll grade it like a real screen (7/10 or better passes).
You've shipped a model that looks fine in offline checks, but its predictions are consistently wrong in practice. The team wants you to figure out why the outputs are so far off and what to inspect first.
How would you approach a situation where your model's predictions are consistently inaccurate?