Your question is Monitor Model Accuracy Over Time. 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 have shipped a model and it was accurate at launch, but the team wants a clear way to tell whether it is still performing well after deployment. The model is now scoring live traffic, and you need to know when its predictions stop matching reality.
How do you ensure your models remain accurate over time once deployed?