{
  "lesson": "19-ai-gateways",
  "title": "AI Gateways — LiteLLM, Portkey, Kong AI Gateway, Bifrost",
  "questions": [
    {
      "stage": "pre",
      "question": "What is the core role of an AI gateway in the lesson?",
      "options": [
        "A vector database for retrieval",
        "A model fine-tuning service",
        "A process sitting between apps and model providers that consolidates routing, fallback, retries, rate limits, secret references, observability, and guardrails behind one API",
        "A logging-only sidecar"
      ],
      "correct": 2,
      "explanation": ""
    },
    {
      "stage": "check",
      "question": "What scale ceiling does Kong's benchmark report for LiteLLM?",
      "options": [
        "LiteLLM cannot be benchmarked",
        "It scales linearly past 10k RPS",
        "It breaks down around ~2000 RPS with 8 GB memory and cascading failures under sustained load",
        "It tops out at 50 RPS"
      ],
      "correct": 2,
      "explanation": ""
    },
    {
      "stage": "check",
      "question": "Per the Kong benchmark on equivalent CPU, how much faster is Kong AI Gateway than Portkey and LiteLLM?",
      "options": [
        "Identical",
        "About 10% and 20% faster",
        "228% faster than Portkey and 859% faster than LiteLLM",
        "Slower than both"
      ],
      "correct": 2,
      "explanation": ""
    },
    {
      "stage": "check",
      "question": "Which gateway does the lesson position with 20-40 ms latency overhead and guardrails / PII redaction / jailbreak detection focus?",
      "options": [
        "Cloudflare AI Gateway",
        "Portkey",
        "Kong AI Gateway",
        "LiteLLM"
      ],
      "correct": 1,
      "explanation": ""
    },
    {
      "stage": "post",
      "question": "What does the lesson say is the forcing function for self-hosted vs managed gateway decisions?",
      "options": [
        "Number of supported providers",
        "Cost per request",
        "Data residency requirements",
        "Whether the gateway is open source"
      ],
      "correct": 2,
      "explanation": ""
    },
    {
      "stage": "post",
      "question": "Which gateways stay within budget when the SLA is TTFT P99 < 100 ms?",
      "options": [
        "Only Portkey",
        "Any gateway",
        "Only LiteLLM",
        "Kong (~3-8 ms) or Cloudflare/Vercel edge gateways (~1-3 ms); Portkey at 20-40 ms is too heavy"
      ],
      "correct": 3,
      "explanation": ""
    }
  ]
}