Interview-style Problems for ML and system design, for rehearsing the reasoning an interview asks for. Work each one the way you would in the room: clarify the requirements, sketch a design, then defend the trade-offs.
Want the ground first? Build it in Tracks, or look up a concept in Knowledge. Problems point back to both.
Design a system that condenses chat, alerts and deploy events from a live incident into a handoff summary, and decide how to tell whether the summary can be trusted.