02 · ObservabilityAverage latency looks healthy, but p99 is timing out. How would you find the cause?
03 · Distributed SystemsA multi-region failover caused inconsistent data. How would you redesign recovery?
07 · Distributed SystemsDuplicate events are creating repeated orders. How would you design idempotency?
12 · AI AgentsOur agent repeats tool calls and creates duplicate side effects. How would you stop it?
15 · Search SystemsVector search misses exact IDs and product names. How would you improve retrieval?
18 · AI ReliabilityA provider rate-limit incident is cascading through our AI product. What would you change?
20 · Context EngineeringOur context window keeps growing until requests fail. How would you control it?