Your question is Messaging System with AI 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).
Design a messenger that supports: 1) sending messages to users, 2) users can see chat history, 3) an external AI service detects inappropriate messages.
Asked in the Phone screen stage.
Address the API and data model, message delivery and history retrieval, synchronous versus asynchronous moderation, external-service failures, and privacy or authorization boundaries. Explain how you would evaluate moderation quality, monitor the system, and prevent training-serving skew if moderation feedback is later used to improve a classifier.