{
  "schemaVersion": 1,
  "generatedAt": "2026-09-15T02:55:35.359704+00:00",
  "status": "completed",
  "sourceCommit": "42ac5b71751073066b785d09d449938eaaa5df96",
  "headline": "Trident single-site pilot",
  "summary": "3 of 3 planned stages have recorded outcomes across 1 provider. 3 of 3 recorded stages have completed source review; 0 planned stages remain unrecorded.",
  "sourceReview": {
    "status": "source_supported_at_observed_times",
    "reviewerKind": "assistant",
    "reviewedStages": 3,
    "recordedStages": 3,
    "plannedStages": 3,
    "allPlannedStagesRecorded": true,
    "entrantVisibleEquivalence": "not_established",
    "supportedNoncampCount": 3,
    "supportedOutsideSeasonCount": 0,
    "unsupportedExtraCount": 0,
    "unresolvedExtraCount": 0,
    "observedAt": [
      "2026-09-15T01:55:56.359484+00:00"
    ],
    "limitations": [
      "Source review describes published support at stated observation times; it does not establish entrant-visible or interactive source equivalence.",
      "Additional-record dispositions do not verify every attribute of an out-of-scope record or change raw fact recovery, unknown-extra counts, or task-pass results.",
      "Failed, skipped, and empty outputs retain their frozen denominators and receive no delivered-fact credit from review.",
      "Review of recorded stages does not cover unfinished planned stages or make an incomplete benchmark final."
    ]
  },
  "scopeReduction": {
    "kind": "post_run_scope_reduction",
    "reason": "User requested a smaller pilot to reduce waiting",
    "originalPlannedStages": 126,
    "selectedStages": 3,
    "selectionRule": "First onboarding attempt for Great Work Montessori from each of the three stacks"
  },
  "priorSetupIncidents": [
    {
      "label": "Prior development setup incident",
      "status": "stopped",
      "plannedStages": 36,
      "recordedStages": 9,
      "completedStages": 4,
      "failedStages": 2,
      "setupFailureStages": 2,
      "includedCreditsUsed": 0.0,
      "resourceCreditsObserved": 96.0,
      "apiCashUsd": null,
      "limitations": [
        "Preserved work and setup incidents are excluded from the selected comparison denominators.",
        "Credit counters are known subtotals where reported; resource credits and billed credits are separate quantities.",
        "Total campaign cost remains unavailable because subscription allocation and local compute are unmeasured."
      ]
    }
  ],
  "ancillaryUsage": {
    "excludedRecordedStages": 2,
    "priorRecordedStages": 9,
    "billedCreditsKnownSubtotal": 0.0,
    "resourceCreditsKnownSubtotal": 213.0,
    "apiCashKnownSubtotalUsd": 0.0,
    "totalCampaignCostUsd": null,
    "limitations": [
      "Ancillary work is excluded from selected comparison denominators and remains part of campaign resource use.",
      "These are sums of known counters only; missing counters are not zero. Resource credits do not establish billed credits or dollar cost.",
      "Main comparison API cash and credits describe selected stages only; total campaign dollar cost is unavailable."
    ]
  },
  "providers": [
    {
      "id": "great-work-montessori",
      "name": "Great Work Montessori",
      "url": "https://greatworkmontessori.com/",
      "cohort": "development",
      "sessionCount": 5,
      "factCount": 40
    }
  ],
  "stages": [
    {
      "id": "e9a92f59fa6d4347:001-great-work-montessori-01-trident-onboarding",
      "providerId": "great-work-montessori",
      "system": "trident",
      "cohort": "development",
      "phase": "onboarding",
      "repetition": 1,
      "status": "completed",
      "terminationReason": "queue_completed",
      "seconds": 504.5587545419112,
      "wallSeconds": 508.82684500003234,
      "correctFacts": 40,
      "expectedFacts": 40,
      "completeSessions": 5,
      "expectedSessions": 5,
      "duplicateCount": 0,
      "unknownExtraCount": 0,
      "wrongFacts": 0,
      "credits": null,
      "resourceCredits": null,
      "modelCalls": 5,
      "usageComplete": true,
      "inputTokens": 188604,
      "outputTokens": 10772,
      "cachedInputTokens": 6912,
      "reasoningOutputTokens": 2769,
      "executionMethod": "onboarding_request"
    },
    {
      "id": "e9a92f59fa6d4347:002-great-work-montessori-01-firecrawl-onboarding",
      "providerId": "great-work-montessori",
      "system": "firecrawl",
      "cohort": "development",
      "phase": "onboarding",
      "repetition": 1,
      "status": "completed",
      "terminationReason": "completed",
      "seconds": 241.0079837909434,
      "wallSeconds": 244.5033732498996,
      "correctFacts": 40,
      "expectedFacts": 40,
      "completeSessions": 5,
      "expectedSessions": 5,
      "duplicateCount": 0,
      "unknownExtraCount": 3,
      "wrongFacts": 0,
      "credits": 0,
      "resourceCredits": 106,
      "modelCalls": null,
      "usageComplete": null,
      "inputTokens": null,
      "outputTokens": null,
      "cachedInputTokens": null,
      "reasoningOutputTokens": null,
      "executionMethod": "fresh_subprocess"
    },
    {
      "id": "e9a92f59fa6d4347:003-great-work-montessori-01-crawl4ai-onboarding",
      "providerId": "great-work-montessori",
      "system": "crawl4ai",
      "cohort": "development",
      "phase": "onboarding",
      "repetition": 1,
      "status": "completed",
      "terminationReason": "completed",
      "seconds": 72.7661449171137,
      "wallSeconds": 72.82112854206935,
      "correctFacts": 40,
      "expectedFacts": 40,
      "completeSessions": 5,
      "expectedSessions": 5,
      "duplicateCount": 0,
      "unknownExtraCount": 0,
      "wrongFacts": 0,
      "credits": null,
      "resourceCredits": null,
      "modelCalls": 1,
      "usageComplete": true,
      "inputTokens": 28770,
      "outputTokens": 3237,
      "cachedInputTokens": 6912,
      "reasoningOutputTokens": 496,
      "executionMethod": null
    }
  ],
  "points": [
    {
      "system": "crawl4ai",
      "cohort": "development",
      "phase": "onboarding",
      "fieldRecovery": 1.0,
      "correctFacts": 40,
      "expectedFacts": 40,
      "medianWallSeconds": 72.82112854206935,
      "minimumWallSeconds": 72.82112854206935,
      "maximumWallSeconds": 72.82112854206935,
      "completed": 1,
      "planned": 1,
      "resolved": 1,
      "completeSessions": 5,
      "expectedSessions": 5,
      "wrongFacts": 0,
      "duplicates": 0,
      "credits": null
    },
    {
      "system": "firecrawl",
      "cohort": "development",
      "phase": "onboarding",
      "fieldRecovery": 1.0,
      "correctFacts": 40,
      "expectedFacts": 40,
      "medianWallSeconds": 244.5033732498996,
      "minimumWallSeconds": 244.5033732498996,
      "maximumWallSeconds": 244.5033732498996,
      "completed": 1,
      "planned": 1,
      "resolved": 1,
      "completeSessions": 5,
      "expectedSessions": 5,
      "wrongFacts": 0,
      "duplicates": 0,
      "credits": 0.0
    },
    {
      "system": "trident",
      "cohort": "development",
      "phase": "onboarding",
      "fieldRecovery": 1.0,
      "correctFacts": 40,
      "expectedFacts": 40,
      "medianWallSeconds": 508.82684500003234,
      "minimumWallSeconds": 508.82684500003234,
      "maximumWallSeconds": 508.82684500003234,
      "completed": 1,
      "planned": 1,
      "resolved": 1,
      "completeSessions": 5,
      "expectedSessions": 5,
      "wrongFacts": 0,
      "duplicates": 0,
      "credits": null
    }
  ],
  "totalApiCashUsd": 0.0,
  "includedCreditsUsed": 0.0,
  "spendingCapUsd": 25,
  "findings": [
    {
      "title": "Three-way tie on core facts",
      "description": "Each stack recovered all 40 established camp facts in its first extraction on this provider. One attempt per stack on one website does not establish broader performance or a general ranking."
    },
    {
      "title": "Reviewed core fact recovery",
      "description": "120 of 120 established fact opportunities are recovered across the planned workload. The separate source review preserves every frozen core score and all pending or failed-stage denominators."
    },
    {
      "title": "First-extraction timing",
      "description": "Each selected point records the first onboarding extraction from one stack on the same provider. Refresh and repeated-attempt work is excluded from these comparison points and retained in ancillary accounting."
    },
    {
      "title": "Cost remains unavailable",
      "description": "Total dollar cost is unavailable because subscription allocation and local compute are unmeasured. Known included-credit use and verified API cash are shown separately."
    },
    {
      "title": "Source review coverage",
      "description": "3 of 3 recorded stages reviewed; source-supported at observed times. Additional records have separate scope dispositions, while raw extra counts and task-pass results remain unchanged."
    },
    {
      "title": "Core facts are a subset",
      "description": "Recovering all established camp facts does not certify every business or activity field, current availability, confirmed venues, or complete fees. Trident's native business result is marked partial."
    },
    {
      "title": "Recorded model calls",
      "description": "Trident recorded 5 model calls; Crawl4AI with Codex recorded 1. Firecrawl internal model-call count is unavailable. These configurations perform different amounts of internal work."
    },
    {
      "title": "Excluded refresh diagnostic",
      "description": "An additional Trident refresh recorded zero model calls and 271.8 seconds of process wall time. It is preserved in ancillary accounting and excluded from the first-extraction comparison."
    },
    {
      "title": "Firecrawl billing and resource counters",
      "description": "1 recorded stage with both counters returned 0 billed credits and recorded 106 trace resource credits. These are distinct quantities; resource counters do not establish cash cost."
    }
  ],
  "limitations": [
    "The user reduced scope after execution began to shorten waiting. The selected comparison uses the first onboarding attempt from every stack on one provider; the original frozen plan and excluded work remain preserved separately. This is a single-site pilot without a general ranking claim.",
    "Source review: source-supported at observed times. Review is attributed to an assistant reviewer and does not establish equivalent entrant-visible source content.",
    "Eight core field groups are scored where reference evidence establishes values. Complete sessions means complete unique recovery of those groups, not verification of every native output field.",
    "Known included credits is the sum of returned Firecrawl billed-credit counters, not a complete total when counters or planned outcomes are missing. Trace resource credits are a separate quantity and do not establish cash cost.",
    "The spending ceiling is the shared configured ceiling, not the sum of per-batch copies of that ceiling.",
    "Token counters are recorded per stage and remain unavailable when unreported. A sum of available counters is only a measured subtotal unless every selected stage reports that counter.",
    "One website and one attempt per stack cannot estimate variation across attempts or providers. This pilot does not support a general ranking.",
    "Core camp recovery does not certify complete business or activity extraction, every returned field, current availability, complete fees, or confirmed session venues."
  ],
  "audit": [
    {
      "label": "Source adjudication",
      "value": "Source-supported at observed times"
    },
    {
      "label": "Planned stages",
      "value": "3"
    },
    {
      "label": "Resolved stages",
      "value": "3"
    },
    {
      "label": "Completed stages",
      "value": "3"
    },
    {
      "label": "Total dollar cost",
      "value": "Unavailable"
    },
    {
      "label": "Timing unit",
      "value": "Seconds per phase; summed seconds per onboarding and refresh chain"
    }
  ]
}
