Your question is Design ML for Message Safety. 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 are building a real-time messaging product where messages should be delivered quickly, but some content must be flagged or blocked before it reaches the recipient. The system needs to score text as messages are sent and support policy updates over time.
How would you design a real-time messaging system?