{
  "benchmark": "AI Handoff Continuity Benchmark",
  "benchmarkVersion": "1.0.0-pilot",
  "submission": {
    "provider": "Anthropic",
    "model": "Claude Code",
    "modelVersion": "claude-sonnet-5",
    "temperature": null,
    "runAt": "2026-08-04T00:00:00+03:00",
    "host": "claude-code 2.1.220",
    "retryPolicy": "No retries; strict JSON parse; malformed responses score as missing."
  },
  "scoredAt": "2026-08-03T21:08:40.259Z",
  "overallScore": 45.19,
  "answered": 9,
  "total": 9,
  "byCondition": [
    {
      "condition": "transcript",
      "label": "Conversation transcript",
      "score": 53.33,
      "answered": 3,
      "total": 3
    },
    {
      "condition": "memory",
      "label": "Compressed memory",
      "score": 23.33,
      "answered": 3,
      "total": 3
    },
    {
      "condition": "handoff",
      "label": "Structured handoff",
      "score": 58.89,
      "answered": 3,
      "total": 3
    }
  ],
  "rows": [
    {
      "caseId": "incident-cache-headers",
      "caseTitle": "Production cache-header incident",
      "condition": "transcript",
      "answered": true,
      "score": 0,
      "dimensions": {
        "objective": {
          "score": 0,
          "maximum": 10
        },
        "currentState": {
          "score": 0,
          "maximum": 20
        },
        "decisions": {
          "score": 0,
          "maximum": 15
        },
        "evidence": {
          "score": 0,
          "maximum": 15
        },
        "constraints": {
          "score": 0,
          "maximum": 10
        },
        "nextAction": {
          "score": 0,
          "maximum": 15
        },
        "owner": {
          "score": 0,
          "maximum": 5
        },
        "openQuestions": {
          "score": 0,
          "maximum": 10
        }
      }
    },
    {
      "caseId": "incident-cache-headers",
      "caseTitle": "Production cache-header incident",
      "condition": "memory",
      "answered": true,
      "score": 0,
      "dimensions": {
        "objective": {
          "score": 0,
          "maximum": 10
        },
        "currentState": {
          "score": 0,
          "maximum": 20
        },
        "decisions": {
          "score": 0,
          "maximum": 15
        },
        "evidence": {
          "score": 0,
          "maximum": 15
        },
        "constraints": {
          "score": 0,
          "maximum": 10
        },
        "nextAction": {
          "score": 0,
          "maximum": 15
        },
        "owner": {
          "score": 0,
          "maximum": 5
        },
        "openQuestions": {
          "score": 0,
          "maximum": 10
        }
      }
    },
    {
      "caseId": "incident-cache-headers",
      "caseTitle": "Production cache-header incident",
      "condition": "handoff",
      "answered": true,
      "score": 86.67,
      "dimensions": {
        "objective": {
          "score": 0,
          "maximum": 10
        },
        "currentState": {
          "score": 20,
          "maximum": 20
        },
        "decisions": {
          "score": 15,
          "maximum": 15
        },
        "evidence": {
          "score": 15,
          "maximum": 15
        },
        "constraints": {
          "score": 6.67,
          "maximum": 10
        },
        "nextAction": {
          "score": 15,
          "maximum": 15
        },
        "owner": {
          "score": 5,
          "maximum": 5
        },
        "openQuestions": {
          "score": 10,
          "maximum": 10
        }
      }
    },
    {
      "caseId": "research-onboarding-dropoff",
      "caseTitle": "Onboarding drop-off research",
      "condition": "transcript",
      "answered": true,
      "score": 90,
      "dimensions": {
        "objective": {
          "score": 0,
          "maximum": 10
        },
        "currentState": {
          "score": 20,
          "maximum": 20
        },
        "decisions": {
          "score": 15,
          "maximum": 15
        },
        "evidence": {
          "score": 15,
          "maximum": 15
        },
        "constraints": {
          "score": 10,
          "maximum": 10
        },
        "nextAction": {
          "score": 15,
          "maximum": 15
        },
        "owner": {
          "score": 5,
          "maximum": 5
        },
        "openQuestions": {
          "score": 10,
          "maximum": 10
        }
      }
    },
    {
      "caseId": "research-onboarding-dropoff",
      "caseTitle": "Onboarding drop-off research",
      "condition": "memory",
      "answered": true,
      "score": 0,
      "dimensions": {
        "objective": {
          "score": 0,
          "maximum": 10
        },
        "currentState": {
          "score": 0,
          "maximum": 20
        },
        "decisions": {
          "score": 0,
          "maximum": 15
        },
        "evidence": {
          "score": 0,
          "maximum": 15
        },
        "constraints": {
          "score": 0,
          "maximum": 10
        },
        "nextAction": {
          "score": 0,
          "maximum": 15
        },
        "owner": {
          "score": 0,
          "maximum": 5
        },
        "openQuestions": {
          "score": 0,
          "maximum": 10
        }
      }
    },
    {
      "caseId": "research-onboarding-dropoff",
      "caseTitle": "Onboarding drop-off research",
      "condition": "handoff",
      "answered": true,
      "score": 0,
      "dimensions": {
        "objective": {
          "score": 0,
          "maximum": 10
        },
        "currentState": {
          "score": 0,
          "maximum": 20
        },
        "decisions": {
          "score": 0,
          "maximum": 15
        },
        "evidence": {
          "score": 0,
          "maximum": 15
        },
        "constraints": {
          "score": 0,
          "maximum": 10
        },
        "nextAction": {
          "score": 0,
          "maximum": 15
        },
        "owner": {
          "score": 0,
          "maximum": 5
        },
        "openQuestions": {
          "score": 0,
          "maximum": 10
        }
      }
    },
    {
      "caseId": "warehouse-refund-model",
      "caseTitle": "Warehouse refund model revision",
      "condition": "transcript",
      "answered": true,
      "score": 70,
      "dimensions": {
        "objective": {
          "score": 0,
          "maximum": 10
        },
        "currentState": {
          "score": 20,
          "maximum": 20
        },
        "decisions": {
          "score": 15,
          "maximum": 15
        },
        "evidence": {
          "score": 15,
          "maximum": 15
        },
        "constraints": {
          "score": 10,
          "maximum": 10
        },
        "nextAction": {
          "score": 0,
          "maximum": 15
        },
        "owner": {
          "score": 0,
          "maximum": 5
        },
        "openQuestions": {
          "score": 10,
          "maximum": 10
        }
      }
    },
    {
      "caseId": "warehouse-refund-model",
      "caseTitle": "Warehouse refund model revision",
      "condition": "memory",
      "answered": true,
      "score": 70,
      "dimensions": {
        "objective": {
          "score": 0,
          "maximum": 10
        },
        "currentState": {
          "score": 20,
          "maximum": 20
        },
        "decisions": {
          "score": 15,
          "maximum": 15
        },
        "evidence": {
          "score": 15,
          "maximum": 15
        },
        "constraints": {
          "score": 10,
          "maximum": 10
        },
        "nextAction": {
          "score": 0,
          "maximum": 15
        },
        "owner": {
          "score": 0,
          "maximum": 5
        },
        "openQuestions": {
          "score": 10,
          "maximum": 10
        }
      }
    },
    {
      "caseId": "warehouse-refund-model",
      "caseTitle": "Warehouse refund model revision",
      "condition": "handoff",
      "answered": true,
      "score": 90,
      "dimensions": {
        "objective": {
          "score": 0,
          "maximum": 10
        },
        "currentState": {
          "score": 20,
          "maximum": 20
        },
        "decisions": {
          "score": 15,
          "maximum": 15
        },
        "evidence": {
          "score": 15,
          "maximum": 15
        },
        "constraints": {
          "score": 10,
          "maximum": 10
        },
        "nextAction": {
          "score": 15,
          "maximum": 15
        },
        "owner": {
          "score": 5,
          "maximum": 5
        },
        "openQuestions": {
          "score": 10,
          "maximum": 10
        }
      }
    }
  ]
}