marketplace/tests/positive-tests.json

[
  {
    "id": "P01-full-initiation",
    "user_prompt": "Perform a full institutional initiation on Microsoft using current public information.",
    "expected_skill_or_workflow": "full-company-analysis plus primary sector playbook and any material secondary playbook.",
    "expected_behavior": [
      "Define scope and as-of date",
      "Use current primary sources first",
      "Build source log and assumption register",
      "Execute relevant core modules",
      "Apply sector protocol",
      "Build driver forecast and valuation",
      "Include contrary evidence and thesis breaks",
      "Run completion gates and Appendix M audit"
    ],
    "expected_output_structure": [
      "Decision Layer",
      "Evidence Layer",
      "Valuation",
      "Risk and falsification",
      "Completion audit"
    ],
    "fixtures": "No private fixture required. Public data only."
  },
  {
    "id": "P02-10k",
    "user_prompt": "Deep-read the latest 10-K for a public company and compare it with the prior 10-K.",
    "expected_skill_or_workflow": "filings-primary-sources.",
    "expected_behavior": [
      "Retrieve exact filed versions",
      "Inspect relevant exhibits and footnotes",
      "Compare disclosure wording and definitions",
      "Reconcile MD&A to statements",
      "Record model or no-action implications"
    ],
    "expected_output_structure": [
      "Filing identification",
      "New/changed facts",
      "Accounting and footnotes",
      "Disclosure drift",
      "Model implications",
      "Open questions"
    ],
    "fixtures": "Public SEC filings."
  },
  {
    "id": "P03-model",
    "user_prompt": "Build a five-year driver model for an industrial company with revenue by units and price, margins, working capital, capex, debt, taxes and diluted shares.",
    "expected_skill_or_workflow": "financial-modeling.",
    "expected_behavior": [
      "Normalize historicals",
      "Forecast causal drivers",
      "Integrate statements",
      "Use scenarios",
      "Run model-break checks",
      "Preserve assumption/change logs"
    ],
    "expected_output_structure": [
      "Historical normalization",
      "Driver forecast",
      "Integrated statements",
      "Scenarios",
      "Checks",
      "Assumptions"
    ],
    "fixtures": "User-provided or public historical data."
  },
  {
    "id": "P04-reverse-dcf",
    "user_prompt": "Reverse DCF this public stock at its current market price.",
    "expected_skill_or_workflow": "valuation.",
    "expected_behavior": [
      "Establish current EV/equity bridge",
      "Solve for implied operating assumptions",
      "Translate implications into native business units",
      "Compare against history/industry",
      "State variant evidence and falsification"
    ],
    "expected_output_structure": [
      "Current valuation bridge",
      "Implied expectations",
      "Operating translation",
      "Reality checks",
      "Sensitivity"
    ],
    "fixtures": "Current market price and public financial data."
  },
  {
    "id": "P05-forensics",
    "user_prompt": "Review this public company for earnings-quality and accounting-manipulation risk without assuming fraud.",
    "expected_skill_or_workflow": "forensic-accounting.",
    "expected_behavior": [
      "Reconstruct cash conversion and accruals",
      "Review non-GAAP adjustments and estimates",
      "Present benign and adverse interpretations",
      "Avoid treating red-flag scores as conclusions",
      "Identify discriminating evidence"
    ],
    "expected_output_structure": [
      "Observed facts",
      "Calculations",
      "Benign case",
      "Adverse case",
      "Evidence needed",
      "Risk impact"
    ],
    "fixtures": "Public filings."
  },
  {
    "id": "P06-sector",
    "user_prompt": "Analyze an airline using the sector-specific playbook.",
    "expected_skill_or_workflow": "sector-analysis, Airlines playbook.",
    "expected_behavior": [
      "Load common sector protocol",
      "Use airline native KPIs",
      "Normalize lease and loyalty economics",
      "Track appropriate leading indicators",
      "Use sector-appropriate valuation",
      "Run capacity/fare/liquidity stress"
    ],
    "expected_output_structure": [
      "KPI history",
      "Leading indicators",
      "Accounting normalization",
      "Forecast",
      "Valuation",
      "Stress and exit-standard audit"
    ],
    "fixtures": "Public airline data."
  },
  {
    "id": "P07-earnings",
    "user_prompt": "Analyze the latest earnings result versus what the prior quarter implied.",
    "expected_skill_or_workflow": "earnings-events.",
    "expected_behavior": [
      "Reconstruct pre-event expectation",
      "Reconcile quarter and YTD data correctly",
      "Attribute revisions to new evidence",
      "Update thesis and valuation",
      "Set next validation datapoints"
    ],
    "expected_output_structure": [
      "Pre-event baseline",
      "Reported bridge",
      "Estimate changes",
      "Thesis impact",
      "Valuation impact",
      "Next checks"
    ],
    "fixtures": "Latest filings and prior guidance."
  },
  {
    "id": "P08-risk",
    "user_prompt": "Stress-test a levered public company for a 20% revenue decline and refinancing shock.",
    "expected_skill_or_workflow": "risk-decision.",
    "expected_behavior": [
      "Translate revenue shock through margins/working capital/cash",
      "Model usable liquidity",
      "Review debt/covenant definitions",
      "Model financing/dilution consequences",
      "Define thesis-break thresholds"
    ],
    "expected_output_structure": [
      "Shock assumptions",
      "Causal transmission",
      "Liquidity and covenant path",
      "Financing/dilution",
      "Valuation downside",
      "Thesis breaks"
    ],
    "fixtures": "Public financial and debt data."
  }
]