Your question is Real-Time Recommendations Under 100ms. 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).
How would you architect a real-time recommendation system for internal Workday users, ensuring latency remains under 100 milliseconds?
Assume the surface is used by employees and internal admins across Workday products, and recommendations may include relevant tasks, reports, knowledge articles, or next-best actions. Focus on the serving architecture, model choices, and how you would keep the system fast, fresh, and reliable.