Your question is Real-Time Recommendation Engine Design. 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).
Design a real-time recommendation engine that updates suggestions based on immediate user actions.
Explain how you would clarify requirements, process behavioral events, update user state, retrieve and rank recommendations, and serve results with low latency. Cover online versus batch computation, feedback-loop design, evaluation, monitoring, feature drift, training-serving skew, and failure recovery. State the assumptions you would request before sizing the system.