1. AI-Era Architecture advanced

    An enterprise AI platform serves many customers on shared inference infrastructure. What isolation is required, and where is the hardest boundary?

    2 min answer coheremulti-tenancyisolationdata
  2. AI-Era Architecture advanced

    An inference platform receives computationally expensive requests in unpredictable bursts. Should it use admission control, request queues, dynamic batching, autoscaling, priority classes or pre-provisioned capacity?

    2 min answer together-aiinferencebatchingadmission-control
  3. AI-Era Architecture advanced

    Legal asks whether customer personal data is being sent to your model provider. What must you be able to answer?

    2 min answer privacyaicompliance
  4. AI-Era Architecture advanced

    You are asked to give an internal AI agent access to the customer database, the ticketing system and outbound email so it can resolve support tickets. What is your response?

    2 min answer agentssecurityprompt-injectionhitl
  5. AI Gateways advanced

    A platform routes all model calls through an internal gateway. What belongs there, and what must not?

    2 min answer ai-gatewayroutingquotascaching
  6. AI Gateways advanced

    An AI gateway now terminates streaming responses for six products and holds a semantic cache shared across tenants. Two properties of that design have caused real outages and real data exposure at large AI providers. What has the organisation taken on and when does the bill arrive?

    3 min answer ai-gatewayopenaiblast-radiussemantic-cache
  7. 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
  8. 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
  9. AI Observability advanced

    A fraud model has been in production for eight months. Ground truth arrives weeks later. How do you know if it is still working?

    2 min answer mlmonitoringdrift
  10. AI Observability advanced

    Anthropic reported in 2025 that a routing bug sent a share of Claude Sonnet 4 requests to servers configured for a different context length, peaking at 16% of those requests in the worst hour on 31 August, and that it took weeks to identify. Error rates never moved. Which design decision allowed the delay and what telemetry closes it?

    3 min answer anthropicpostmortemsilent-regressionrouting
  11. AI Observability advanced

    What must be observable in an AI feature that is not covered by conventional application monitoring?

    2 min answer ai-observabilitytracingqualitycost
  12. AI Observability advanced

    You are asked to log every prompt and response for an assistant handling 2 million interactions a day, so quality regressions are diagnosable. Roughly how much data does that commit you to per year, and does the number change the design?

    3 min answer observabilityloggingretentioncost