{
  "lesson": "26-failure-modes-agentic",
  "title": "Failure Modes: Why Agents Break",
  "questions": [
    {
      "stage": "pre",
      "question": "What is MASFT's central claim?",
      "options": [
        "Failures are random noise",
        "Failures are due to network outages",
        "Failures vanish with bigger models",
        "Multi-agent failures are fundamental design flaws, not LLM limitations to be fixed with better base models"
      ],
      "correct": 3,
      "explanation": "Berkeley's MASFT categorizes failures as design flaws; they do not disappear by scaling the base model."
    },
    {
      "stage": "pre",
      "question": "Which is NOT one of the five recurring industry failure modes the lesson lists?",
      "options": [
        "Hallucinated actions",
        "Cascading errors",
        "Scope creep",
        "Embedding versioning"
      ],
      "correct": 3,
      "explanation": "The five are hallucinated actions, scope creep, cascading errors, context loss, tool misuse."
    },
    {
      "stage": "check",
      "question": "What is a cascading error in this lesson?",
      "options": [
        "A YAML parser error",
        "One wrong call triggers downstream effects across systems (a phantom SKU triggers four downstream API calls)",
        "A cron failure",
        "An LLM rate-limit cascade"
      ],
      "correct": 1,
      "explanation": "Cascades amplify a single bad call into a multi-system incident; especially severe when agents fake success."
    },
    {
      "stage": "check",
      "question": "Which two manifestations does the LLM Agent Hallucinations Survey list?",
      "options": [
        "Hot and cold tokens",
        "Instruction-following Deviation and Long-range Contextual Misuse",
        "Greedy and beam search",
        "Soft and hard prompts"
      ],
      "correct": 1,
      "explanation": "Hallucinations show up as either ignoring system prompt or forgetting/misapplying earlier-turn context."
    },
    {
      "stage": "check",
      "question": "What does success hallucination mean?",
      "options": [
        "A unit test passed",
        "The agent returns a success message even though the target state did not change (often on a 400 from a tool)",
        "The user thinks success when none happened",
        "The model is overconfident on benchmarks"
      ],
      "correct": 1,
      "explanation": "Re-probe environment state; agents commonly fake completion when they cannot distinguish 'I failed' from 'impossible'."
    },
    {
      "stage": "post",
      "question": "Why is tagging only crashes insufficient?",
      "options": [
        "Logging is paid",
        "Most agent failures produce valid-looking output that does not crash; content-level checks are needed",
        "Crashes leak PII",
        "Crashes are slow"
      ],
      "correct": 1,
      "explanation": "Crash-based monitoring misses the bulk of agent failures, which are content-shaped."
    },
    {
      "stage": "post",
      "question": "What mitigation does the lesson recommend at every step of a reasoning chain?",
      "options": [
        "Add a sleep()",
        "Disable retries",
        "Automated verification gates that check factual grounding against environment state",
        "Lower temperature only"
      ],
      "correct": 2,
      "explanation": "Per-step gates (safety classifier, argument validation, CRITIC, state re-probe) catch failures before they cascade."
    }
  ]
}