1. AI Cost Management intermediate

    A product embeds model calls in several features and spend is growing unpredictably. What controls actually bound it?

    2 min answer posthogcosttokenscaching
  2. AI-Era Architecture intermediate Multiple choice

    A client wants an assistant that answers questions from 50,000 internal documents which change weekly. RAG or fine-tuning? What actually determines the quality?

    2 min answer ragllmretrievalarchitecture
  3. AI Gateways intermediate

    Several product teams call model providers directly. What does introducing an AI gateway buy, and what does it cost?

    2 min answer credgatewayabstractioncost
  4. AI Gateways intermediate

    Six teams are calling model providers directly from their applications. Justify an AI gateway, and say what it should not do.

    2 min answer platformgovernancecost
  5. Alert Fatigue intermediate

    A team has 340 alerts. On-call receives roughly 40 pages a week and most are ignored. What would you change?

    2 min answer alertingfatigueslooncall
  6. Alert Fatigue intermediate Multiple choice

    A team receives hundreds of alerts a day and misses a genuine outage. What is the fastest structural fix, and what should replace the current approach?

    2 min answer olaalertingfatiguesymptoms
  7. Alert Fatigue intermediate

    An on-call engineer receives so many alerts that they routinely acknowledge without reading. What has failed, and what is the risk beyond tiredness?

    2 min answer alert-fatiguesignal-to-noisereliabilityinstacart
  8. Alert Fatigue intermediate

    An on-call team receives 60 alerts per shift and has stopped reading most of them. What is the structural fix, and what should the alerting rules actually be based on?

    3 min answer alertingoncallslosymptom-based
  9. Alert Fatigue intermediate

    Half your pages result in no action being taken. How do you fix that without reducing coverage?

    2 min answer alertingsymptom-basedsloburn-rate
  10. Alerting intermediate

    A platform's alerts are defined per component - CPU, memory, queue depth, replica lag. During an incident, forty alerts fire simultaneously. What should the alerting strategy be instead?

    2 min answer alertingsymptomscausesslo-based
  11. Alerting intermediate

    What is the test for whether an alert should exist, and what does applying it honestly do?

    2 min answer alertingactionabilitysymptomsburn-rate
  12. Analytics Cost Control intermediate

    An analytical platform's cost has grown faster than its usage. Which controls actually reduce it?

    2 min answer snowflakecostauto-suspendlayout