{
  "id": "TKICUcmRUxEUwnxl",
  "name": "AI multi-agent Quantum Fab monitoring with gpt-4 and automated alerts",
  "tags": [],
  "nodes": [
    {
      "id": "f82ca835-772a-4767-bd33-1182915c197a",
      "name": "Monitor Every 30 Minutes",
      "type": "n8n-nodes-base.scheduleTrigger",
      "position": [
        -272,
        1120
      ],
      "parameters": {
        "rule": {
          "interval": [
            {
              "field": "minutes",
              "minutesInterval": 30
            }
          ]
        }
      },
      "typeVersion": 1.3
    },
    {
      "id": "983ea3b7-4027-4042-bb8a-e77ed310a920",
      "name": "Device Characterization Agent",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "position": [
        96,
        208
      ],
      "parameters": {
        "text": "Analyze the quantum device measurements and characterize performance. Focus on:\n1. Qubit coherence times (T1 relaxation time and T2 dephasing time)\n2. Gate fidelity measurements\n3. Device reliability metrics\n4. Performance trends and anomalies\n5. Comparison against target specifications\n\nUse the \"Fetch Device Measurements\" tool to retrieve current data.",
        "options": {
          "maxIterations": 15,
          "systemMessage": "You are an expert quantum device characterization specialist. Your role is to analyze real-time measurement data from quantum computing devices, evaluate key performance metrics including qubit coherence times (T1 and T2), gate fidelity, and device reliability. You have access to the \"Fetch Device Measurements\" tool to retrieve current device data. Provide detailed technical analysis with specific numerical values and identify any performance degradation or anomalies."
        },
        "promptType": "define",
        "hasOutputParser": true
      },
      "typeVersion": 3.1
    },
    {
      "id": "29318921-9ecc-4c69-a185-bd90eceba6c2",
      "name": "OpenAI GPT-5 Model",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        104,
        432
      ],
      "parameters": {
        "model": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-5-mini"
        },
        "options": {
          "maxTokens": 4000,
          "temperature": 0.2
        },
        "builtInTools": {}
      },
      "credentials": {
        "openAiApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1.3
    },
    {
      "id": "221816e1-a4c9-4d78-a18e-6e96bd847eaa",
      "name": "Analysis Output Parser",
      "type": "@n8n/n8n-nodes-langchain.outputParserStructured",
      "position": [
        232,
        432
      ],
      "parameters": {
        "jsonSchemaExample": {
          "actionItems": [],
          "deviceStatus": "operational",
          "qubitMetrics": {
            "gateFidelity": 0.9987,
            "t2DephasingTime": 42.1,
            "t1RelaxationTime": 85.3,
            "deviceReliability": 0.995
          },
          "defectsDetected": [],
          "overallAssessment": "All systems nominal",
          "supplyChainAlerts": [],
          "fabricationOptimizations": [],
          "maintenanceRecommendations": []
        }
      },
      "typeVersion": 1.3
    },
    {
      "id": "f67df8c3-8e8f-414a-8929-901c37c6b4dd",
      "name": "Combine Agent Analyses",
      "type": "n8n-nodes-base.merge",
      "position": [
        448,
        1064
      ],
      "parameters": {
        "numberInputs": 5
      },
      "typeVersion": 3.2
    },
    {
      "id": "9b3162b2-eb75-481e-b580-1c0b68374062",
      "name": "Fabrication Optimization Agent",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "position": [
        96,
        608
      ],
      "parameters": {
        "text": "Analyze fabrication parameters and optimize the manufacturing process. Focus on:\n1. Process parameter analysis (temperature, pressure, deposition rates)\n2. Yield optimization opportunities\n3. Quality control metrics\n4. Process stability and consistency\n5. Recommendations for parameter adjustments\n\nUse \"Fetch Fabrication Parameters\" to get current settings and \"Update Fabrication Parameters\" to apply optimizations.",
        "options": {
          "maxIterations": 15,
          "systemMessage": "You are a quantum fabrication process optimization expert. Your role is to analyze manufacturing parameters, identify opportunities to improve yield and device performance, and recommend process adjustments. You have access to \"Fetch Fabrication Parameters\" to retrieve current settings and \"Update Fabrication Parameters\" to apply optimizations. Base recommendations on data-driven analysis and industry best practices for quantum device fabrication."
        },
        "promptType": "define",
        "hasOutputParser": true
      },
      "typeVersion": 3.1
    },
    {
      "id": "d07e24f8-37c0-40a9-8f28-57e3a363bd79",
      "name": "Defect Detection Agent",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "position": [
        96,
        1008
      ],
      "parameters": {
        "text": "Detect and classify defects in quantum devices and fabrication processes. Focus on:\n1. Identifying anomalies in device measurements\n2. Classifying defect types (material, process, design)\n3. Root cause analysis\n4. Severity assessment\n5. Corrective action recommendations\n\nUse \"Fetch Device Measurements\" to analyze device data for defects.",
        "options": {
          "maxIterations": 15,
          "systemMessage": "You are a quantum device defect detection and classification specialist. Your role is to identify defects, process flaws, and anomalies in quantum devices through analysis of measurement data and fabrication parameters. You have access to \"Fetch Device Measurements\" to retrieve device data. Classify defects by type, severity, and root cause, and provide specific recommendations for corrective actions."
        },
        "promptType": "define",
        "hasOutputParser": true
      },
      "typeVersion": 3.1
    },
    {
      "id": "7a451c4f-2269-4123-9d79-746765922a0d",
      "name": "Supply Chain Monitoring Agent",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "position": [
        96,
        1408
      ],
      "parameters": {
        "text": "Monitor supply chain and material availability for quantum device fabrication. Focus on:\n1. Critical material inventory levels\n2. Component availability and lead times\n3. Supply chain risk assessment\n4. Procurement recommendations\n5. Alternative supplier identification\n\nUse \"Fetch Supply Chain Data\" to retrieve current inventory and supplier information.",
        "options": {
          "maxIterations": 15,
          "systemMessage": "You are a supply chain and materials management specialist for quantum device manufacturing. Your role is to monitor material and component availability, assess supply chain risks, and ensure continuous production capability. You have access to \"Fetch Supply Chain Data\" to retrieve inventory levels and supplier information. Provide proactive alerts for low inventory, long lead times, or supply chain disruptions."
        },
        "promptType": "define",
        "hasOutputParser": true
      },
      "typeVersion": 3.1
    },
    {
      "id": "05d992ce-9975-423b-9b46-c262b24c553f",
      "name": "Predictive Maintenance Agent",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "position": [
        96,
        1824
      ],
      "parameters": {
        "text": "Provide predictive maintenance and decision support for quantum fabrication systems. Focus on:\n1. Equipment health monitoring\n2. Predictive failure analysis\n3. Maintenance scheduling optimization\n4. Downtime minimization strategies\n5. Critical system alerts\n\nUse \"Fetch Device Measurements\" and \"Fetch Fabrication Parameters\" to assess system health, and \"Trigger Maintenance Alert\" when intervention is needed.",
        "options": {
          "maxIterations": 15,
          "systemMessage": "You are a predictive maintenance and decision support specialist for quantum fabrication facilities. Your role is to monitor equipment health, predict potential failures, optimize maintenance schedules, and provide strategic decision support. You have access to \"Fetch Device Measurements\", \"Fetch Fabrication Parameters\", and \"Trigger Maintenance Alert\" tools. Use data-driven analysis to prevent unplanned downtime and optimize operational efficiency."
        },
        "promptType": "define",
        "hasOutputParser": true
      },
      "typeVersion": 3.1
    },
    {
      "id": "1661bd98-3c1e-42f0-85fd-d205f3449914",
      "name": "Consolidate Findings",
      "type": "n8n-nodes-base.aggregate",
      "position": [
        672,
        1112
      ],
      "parameters": {
        "options": {},
        "aggregate": "aggregateAllItemData",
        "destinationFieldName": "agentReports"
      },
      "typeVersion": 1
    },
    {
      "id": "3167dba4-56a6-4eff-a64c-03e0a2b05c96",
      "name": "Synthesis & Reporting Agent",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "position": [
        896,
        1112
      ],
      "parameters": {
        "text": "=Synthesize all agent analyses into a comprehensive quantum fabrication quality assurance report.\n\nAgent Reports:\n{{ $json.agentReports }}\n\nProvide:\n1. Executive summary of overall system status\n2. Consolidated device performance metrics\n3. Critical issues requiring immediate attention\n4. Optimization opportunities ranked by impact\n5. Supply chain status and risks\n6. Prioritized maintenance actions\n7. Recommended actions with timelines",
        "options": {
          "maxIterations": 10,
          "systemMessage": "You are a senior quantum fabrication quality assurance director. Your role is to synthesize analyses from multiple specialized agents (device characterization, fabrication optimization, defect detection, supply chain, and predictive maintenance) into a comprehensive executive report. Prioritize findings by business impact, identify cross-functional dependencies, and provide clear, actionable recommendations with specific timelines. Focus on continuous improvement and operational excellence."
        },
        "promptType": "define",
        "hasOutputParser": true
      },
      "typeVersion": 3.1
    },
    {
      "id": "e2f55ba0-9fa5-427f-9d1a-64b22777f4ce",
      "name": "Synthesis Output Parser",
      "type": "@n8n/n8n-nodes-langchain.outputParserStructured",
      "position": [
        1032,
        1336
      ],
      "parameters": {
        "jsonSchemaExample": {
          "criticalIssues": [],
          "nextReviewDate": "2024-01-15T10:00:00Z",
          "executiveSummary": "Overall system status and key findings",
          "devicePerformance": {
            "status": "operational",
            "t1Average": 85.3,
            "t2Average": 42.1,
            "reliabilityScore": 0.995,
            "gateFidelityAverage": 0.9987
          },
          "supplyChainStatus": "stable",
          "recommendedActions": [],
          "maintenancePriorities": [],
          "optimizationOpportunities": []
        }
      },
      "typeVersion": 1.3
    },
    {
      "id": "460a272d-a068-494a-b638-b8cb6ce5a057",
      "name": "Save QA Report",
      "type": "n8n-nodes-base.dataTable",
      "position": [
        1248,
        1208
      ],
      "parameters": {
        "columns": {
          "value": {
            "t1Average": "={{ $json.output.devicePerformance.t1Average }}",
            "t2Average": "={{ $json.output.devicePerformance.t2Average }}",
            "timestamp": "={{ $now.toISO() }}",
            "nextReview": "={{ $json.output.nextReviewDate }}",
            "reliability": "={{ $json.output.devicePerformance.reliabilityScore }}",
            "deviceStatus": "={{ $json.output.devicePerformance.status }}",
            "gateFidelity": "={{ $json.output.devicePerformance.gateFidelityAverage }}",
            "optimizations": "={{ JSON.stringify($json.output.optimizationOpportunities) }}",
            "criticalIssues": "={{ JSON.stringify($json.output.criticalIssues) }}",
            "executiveSummary": "={{ $json.output.executiveSummary }}",
            "supplyChainStatus": "={{ $json.output.supplyChainStatus }}",
            "recommendedActions": "={{ JSON.stringify($json.output.recommendedActions) }}",
            "maintenancePriorities": "={{ JSON.stringify($json.output.maintenancePriorities) }}"
          },
          "mappingMode": "defineBelow"
        },
        "options": {},
        "dataTableId": {
          "__rl": true,
          "mode": "list",
          "value": ""
        }
      },
      "typeVersion": 1.1
    },
    {
      "id": "7a96e131-515c-4e1f-9266-b61fdca6a3c1",
      "name": "Check Critical Issues",
      "type": "n8n-nodes-base.if",
      "position": [
        1248,
        1016
      ],
      "parameters": {
        "options": {},
        "conditions": {
          "options": {
            "version": 1,
            "leftValue": "",
            "caseSensitive": true,
            "typeValidation": "strict"
          },
          "combinator": "or",
          "conditions": [
            {
              "operator": {
                "type": "number",
                "operation": "gt"
              },
              "leftValue": "={{ $json.output.criticalIssues.length }}",
              "rightValue": 0
            },
            {
              "operator": {
                "type": "string",
                "operation": "equals"
              },
              "leftValue": "={{ $json.output.devicePerformance.status }}",
              "rightValue": "degraded"
            }
          ]
        }
      },
      "typeVersion": 2.3
    },
    {
      "id": "99ed40a4-f060-40ac-8fc2-eac4c5f27986",
      "name": "Send Critical Alert",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        1504,
        992
      ],
      "parameters": {
        "url": "<__PLACEHOLDER_VALUE__Alert notification endpoint (e.g., Slack webhook, email API, or PagerDuty)__>",
        "method": "POST",
        "options": {},
        "jsonBody": "={{ { \"alert\": \"CRITICAL: Quantum Fabrication QA Alert\", \"summary\": $json.output.executiveSummary, \"issues\": $json.output.criticalIssues, \"timestamp\": $now.toISO() } }}",
        "sendBody": true,
        "specifyBody": "json",
        "authentication": "genericCredentialType",
        "genericAuthType": "httpHeaderAuth"
      },
      "typeVersion": 4.4
    },
    {
      "id": "f79efc88-4018-4105-a376-82dbc8a9656e",
      "name": "Log Normal Operation",
      "type": "n8n-nodes-base.set",
      "position": [
        1504,
        1216
      ],
      "parameters": {
        "options": {},
        "assignments": {
          "assignments": [
            {
              "id": "1",
              "name": "status",
              "type": "string",
              "value": "normal"
            },
            {
              "id": "2",
              "name": "message",
              "type": "string",
              "value": "No critical issues detected"
            },
            {
              "id": "3",
              "name": "timestamp",
              "type": "string",
              "value": "={{ $now.toISO() }}"
            }
          ]
        }
      },
      "typeVersion": 3.4
    },
    {
      "id": "db726185-ec8a-43f1-848b-5efc3fbece4b",
      "name": "OpenAI GPT-5 Model1",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        912,
        1456
      ],
      "parameters": {
        "model": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-5-mini"
        },
        "options": {
          "maxTokens": 4000,
          "temperature": 0.2
        },
        "builtInTools": {}
      },
      "credentials": {
        "openAiApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1.3
    },
    {
      "id": "a7e70fa1-88e4-40ef-be29-e7238f770971",
      "name": "OpenAI GPT-5 Model2",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        104,
        832
      ],
      "parameters": {
        "model": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-5-mini"
        },
        "options": {
          "maxTokens": 4000,
          "temperature": 0.2
        },
        "builtInTools": {}
      },
      "credentials": {
        "openAiApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1.3
    },
    {
      "id": "dccf707b-37fb-4464-9591-ef891a5313df",
      "name": "Analysis Output Parser1",
      "type": "@n8n/n8n-nodes-langchain.outputParserStructured",
      "position": [
        232,
        832
      ],
      "parameters": {
        "jsonSchemaExample": {
          "actionItems": [],
          "deviceStatus": "operational",
          "qubitMetrics": {
            "gateFidelity": 0.9987,
            "t2DephasingTime": 42.1,
            "t1RelaxationTime": 85.3,
            "deviceReliability": 0.995
          },
          "defectsDetected": [],
          "overallAssessment": "All systems nominal",
          "supplyChainAlerts": [],
          "fabricationOptimizations": [],
          "maintenanceRecommendations": []
        }
      },
      "typeVersion": 1.3
    },
    {
      "id": "1f5a0101-0c78-4f84-9eaf-3e1afc58a6a6",
      "name": "OpenAI GPT-5 Model3",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        104,
        1232
      ],
      "parameters": {
        "model": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-5-mini"
        },
        "options": {
          "maxTokens": 4000,
          "temperature": 0.2
        },
        "builtInTools": {}
      },
      "credentials": {
        "openAiApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1.3
    },
    {
      "id": "9490d93a-e7ad-4c98-8766-d7332ce252ad",
      "name": "Analysis Output Parser2",
      "type": "@n8n/n8n-nodes-langchain.outputParserStructured",
      "position": [
        232,
        1232
      ],
      "parameters": {
        "jsonSchemaExample": {
          "actionItems": [],
          "deviceStatus": "operational",
          "qubitMetrics": {
            "gateFidelity": 0.9987,
            "t2DephasingTime": 42.1,
            "t1RelaxationTime": 85.3,
            "deviceReliability": 0.995
          },
          "defectsDetected": [],
          "overallAssessment": "All systems nominal",
          "supplyChainAlerts": [],
          "fabricationOptimizations": [],
          "maintenanceRecommendations": []
        }
      },
      "typeVersion": 1.3
    },
    {
      "id": "3448ee71-e813-439a-85e1-93aa1bbc7a5f",
      "name": "OpenAI GPT-5 Model4",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        104,
        1632
      ],
      "parameters": {
        "model": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-5-mini"
        },
        "options": {
          "maxTokens": 4000,
          "temperature": 0.2
        },
        "builtInTools": {}
      },
      "credentials": {
        "openAiApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1.3
    },
    {
      "id": "aaf1f55c-dc1a-4fcd-88e6-4dcdf0fb7792",
      "name": "Analysis Output Parser3",
      "type": "@n8n/n8n-nodes-langchain.outputParserStructured",
      "position": [
        232,
        1632
      ],
      "parameters": {
        "jsonSchemaExample": {
          "actionItems": [],
          "deviceStatus": "operational",
          "qubitMetrics": {
            "gateFidelity": 0.9987,
            "t2DephasingTime": 42.1,
            "t1RelaxationTime": 85.3,
            "deviceReliability": 0.995
          },
          "defectsDetected": [],
          "overallAssessment": "All systems nominal",
          "supplyChainAlerts": [],
          "fabricationOptimizations": [],
          "maintenanceRecommendations": []
        }
      },
      "typeVersion": 1.3
    },
    {
      "id": "60fc8270-c2a4-40e3-9d77-5d30490b461a",
      "name": "OpenAI GPT-5 Model5",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        96,
        2032
      ],
      "parameters": {
        "model": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-5-mini"
        },
        "options": {
          "maxTokens": 4000,
          "temperature": 0.2
        },
        "builtInTools": {}
      },
      "credentials": {
        "openAiApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1.3
    },
    {
      "id": "3200f9fe-80ed-42d1-82f6-188eac8804eb",
      "name": "Analysis Output Parser4",
      "type": "@n8n/n8n-nodes-langchain.outputParserStructured",
      "position": [
        224,
        2032
      ],
      "parameters": {
        "jsonSchemaExample": {
          "actionItems": [],
          "deviceStatus": "operational",
          "qubitMetrics": {
            "gateFidelity": 0.9987,
            "t2DephasingTime": 42.1,
            "t1RelaxationTime": 85.3,
            "deviceReliability": 0.995
          },
          "defectsDetected": [],
          "overallAssessment": "All systems nominal",
          "supplyChainAlerts": [],
          "fabricationOptimizations": [],
          "maintenanceRecommendations": []
        }
      },
      "typeVersion": 1.3
    },
    {
      "id": "5c5d35e3-1fce-40ae-90c7-3019d3916587",
      "name": "Sticky Note",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1328,
        256
      ],
      "parameters": {
        "color": 4,
        "width": 368,
        "height": 448,
        "content": "## Prerequisites\n- OpenAI API key (GPT-4 access)\n- n8n instance (cloud or self-hosted)\n- Webhook endpoint for alerts\n\n## Use Cases\n- Semiconductor fab line defect monitoring\n- Predictive equipment maintenance scheduling\n\n## Customization\n- Swap GPT-4 for any OpenAI-compatible model\n- Add or remove agent branches for different production domains\n\n## Benefits\n- Eliminates manual QA checks across five production domains simultaneously\n- Cuts defect response time with real-time AI analysis"
      },
      "typeVersion": 1
    },
    {
      "id": "d5b31691-ff78-4854-951d-924db97e292d",
      "name": "Sticky Note1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -304,
        64
      ],
      "parameters": {
        "color": 7,
        "width": 688,
        "height": 2144,
        "content": "##  Input & Five Parallel AI Agents\nWhat: Runs Device Characterization, Fabrication Optimization, Defect Detection, Supply Chain, and Predictive Maintenance agents simultaneously.\nWhy: Covers all critical manufacturing domains in parallel."
      },
      "typeVersion": 1
    },
    {
      "id": "ddec9976-08c8-4b6e-b8ee-2dbb69eb3959",
      "name": "Sticky Note2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        944,
        256
      ],
      "parameters": {
        "width": 288,
        "height": 288,
        "content": "## Setup Steps\n1. Add OpenAI credentials to all five agent nodes and the Synthesis Agent node.\n2. Configure the 30-minute Schedule Trigger interval as needed.\n3. Set the webhook URL in Send Critical Alert node for your alerting system (Slack, PagerDuty, etc.).\n4. Connect a storage destination (Google Sheets, Airtable, or file node) to Save QA Report.\n"
      },
      "typeVersion": 1
    },
    {
      "id": "0cdacdf5-e398-4209-b83d-536a9cbe2e90",
      "name": "Sticky Note3",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        464,
        256
      ],
      "parameters": {
        "width": 416,
        "height": 400,
        "content": "## How It Works\nThis workflow automates manufacturing quality assurance by running five parallel AI agents every 30 minutes. Each agent targets a distinct domain, Device Characterization, Fabrication Optimization, Defect Detection, Supply Chain Monitoring, and Predictive Maintenance using OpenAI GPT-4 models to analyse live production data. Each agent passes its parsed output to a central aggregation step that consolidates all findings into a unified dataset. A Synthesis & Reporting Agent then interprets the combined results and generates a structured QA report. A conditional check evaluates report severity: critical issues trigger an immediate webhook alert, while normal operations are logged quietly. The final report is saved to persistent storage. This template targets manufacturing engineers, ops teams, and plant managers who need continuous, hands-off AI-driven oversight across multiple production systems without building custom monitoring infrastructure from scratch."
      },
      "typeVersion": 1
    },
    {
      "id": "69f15f4c-0fec-4de7-91a7-87a6e5beb7e6",
      "name": "Sticky Note4",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        400,
        816
      ],
      "parameters": {
        "color": 7,
        "width": 208,
        "height": 720,
        "content": "## Combine Agent Analyses\nWhat: Aggregates all five parsed outputs into one dataset.\nWhy: Provides a unified view for holistic synthesis."
      },
      "typeVersion": 1
    },
    {
      "id": "9e779210-c970-48bf-a2f2-f34daaf2ab36",
      "name": "Sticky Note5",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        624,
        816
      ],
      "parameters": {
        "color": 7,
        "width": 208,
        "height": 800,
        "content": "## Consolidate Findings\nWhat: Structures the merged data for the reporting agent.\nWhy: Ensures consistent format before synthesis."
      },
      "typeVersion": 1
    },
    {
      "id": "dfa1a02a-f729-4d6d-8603-24347d1d8cae",
      "name": "Sticky Note6",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1168,
        816
      ],
      "parameters": {
        "color": 7,
        "width": 224,
        "height": 672,
        "content": "## Check Critical Issues\nWhat: Evaluates severity of the report.\nWhy: Routes workflow to alert or log path accordingly."
      },
      "typeVersion": 1
    },
    {
      "id": "7887c86d-0972-4500-ad29-78fe87008a95",
      "name": "Sticky Note7",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        864,
        816
      ],
      "parameters": {
        "color": 7,
        "width": 288,
        "height": 800,
        "content": "\n## Synthesis & Reporting Agent\nWhat: GPT-4 generates a comprehensive QA report.\nWhy: Translates raw agent outputs into actionable insights."
      },
      "typeVersion": 1
    },
    {
      "id": "34577351-51b9-4e7f-b328-a3b0af4c895e",
      "name": "Sticky Note8",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1408,
        768
      ],
      "parameters": {
        "color": 7,
        "width": 304,
        "height": 720,
        "content": "\n## Send Alert / Log / Save Report\nWhat: Sends webhook alert, logs normal status, and saves QA report.\nWhy: Ensures correct stakeholder notification and audit trail."
      },
      "typeVersion": 1
    }
  ],
  "active": false,
  "settings": {
    "binaryMode": "separate",
    "executionOrder": "v1"
  },
  "versionId": "e78b8e46-ad52-4876-8ef0-73901d41f0b4",
  "connections": {
    "OpenAI GPT-5 Model": {
      "ai_languageModel": [
        [
          {
            "node": "Device Characterization Agent",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "OpenAI GPT-5 Model1": {
      "ai_languageModel": [
        [
          {
            "node": "Synthesis & Reporting Agent",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "OpenAI GPT-5 Model2": {
      "ai_languageModel": [
        [
          {
            "node": "Fabrication Optimization Agent",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "OpenAI GPT-5 Model3": {
      "ai_languageModel": [
        [
          {
            "node": "Defect Detection Agent",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "OpenAI GPT-5 Model4": {
      "ai_languageModel": [
        [
          {
            "node": "Supply Chain Monitoring Agent",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "OpenAI GPT-5 Model5": {
      "ai_languageModel": [
        [
          {
            "node": "Predictive Maintenance Agent",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Consolidate Findings": {
      "main": [
        [
          {
            "node": "Synthesis & Reporting Agent",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Check Critical Issues": {
      "main": [
        [
          {
            "node": "Send Critical Alert",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Log Normal Operation",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Analysis Output Parser": {
      "ai_outputParser": [
        [
          {
            "node": "Device Characterization Agent",
            "type": "ai_outputParser",
            "index": 0
          }
        ]
      ]
    },
    "Combine Agent Analyses": {
      "main": [
        [
          {
            "node": "Consolidate Findings",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Defect Detection Agent": {
      "main": [
        [
          {
            "node": "Combine Agent Analyses",
            "type": "main",
            "index": 2
          }
        ]
      ]
    },
    "Analysis Output Parser1": {
      "ai_outputParser": [
        [
          {
            "node": "Fabrication Optimization Agent",
            "type": "ai_outputParser",
            "index": 0
          }
        ]
      ]
    },
    "Analysis Output Parser2": {
      "ai_outputParser": [
        [
          {
            "node": "Defect Detection Agent",
            "type": "ai_outputParser",
            "index": 0
          }
        ]
      ]
    },
    "Analysis Output Parser3": {
      "ai_outputParser": [
        [
          {
            "node": "Supply Chain Monitoring Agent",
            "type": "ai_outputParser",
            "index": 0
          }
        ]
      ]
    },
    "Analysis Output Parser4": {
      "ai_outputParser": [
        [
          {
            "node": "Predictive Maintenance Agent",
            "type": "ai_outputParser",
            "index": 0
          }
        ]
      ]
    },
    "Synthesis Output Parser": {
      "ai_outputParser": [
        [
          {
            "node": "Synthesis & Reporting Agent",
            "type": "ai_outputParser",
            "index": 0
          }
        ]
      ]
    },
    "Monitor Every 30 Minutes": {
      "main": [
        [
          {
            "node": "Device Characterization Agent",
            "type": "main",
            "index": 0
          },
          {
            "node": "Fabrication Optimization Agent",
            "type": "main",
            "index": 0
          },
          {
            "node": "Defect Detection Agent",
            "type": "main",
            "index": 0
          },
          {
            "node": "Supply Chain Monitoring Agent",
            "type": "main",
            "index": 0
          },
          {
            "node": "Predictive Maintenance Agent",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Synthesis & Reporting Agent": {
      "main": [
        [
          {
            "node": "Save QA Report",
            "type": "main",
            "index": 0
          },
          {
            "node": "Check Critical Issues",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Predictive Maintenance Agent": {
      "main": [
        [
          {
            "node": "Combine Agent Analyses",
            "type": "main",
            "index": 4
          }
        ]
      ]
    },
    "Device Characterization Agent": {
      "main": [
        [
          {
            "node": "Combine Agent Analyses",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Supply Chain Monitoring Agent": {
      "main": [
        [
          {
            "node": "Combine Agent Analyses",
            "type": "main",
            "index": 3
          }
        ]
      ]
    },
    "Fabrication Optimization Agent": {
      "main": [
        [
          {
            "node": "Combine Agent Analyses",
            "type": "main",
            "index": 1
          }
        ]
      ]
    }
  }
}