AI Grader

The workflow JSON

Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →

{
  "name": "My workflow",
  "nodes": [
    {
      "parameters": {
        "model": {
          "__rl": true,
          "value": "llama-3.3-70b-versatile",
          "mode": "list",
          "cachedResultName": "llama-3.3-70b-versatile"
        },
        "builtInTools": {},
        "options": {}
      },
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "typeVersion": 1.3,
      "position": [
        144,
        192
      ],
      "id": "064e5295-4458-4a30-89fa-de67726fc623",
      "name": "OpenAI Chat Model",
      "notesInFlow": false,
      "credentials": {
        "openAiApi": {
          "name": "<your credential>"
        }
      }
    },
    {
      "parameters": {
        "promptType": "define",
        "text": "=ROLE:\nAnda adalah Asisten Dosen Senior yang objektif, teliti, dan tegas.\n\nINSTRUCTION:\n1. Bandingkan \"Jawaban Mahasiswa\" dengan \"Kunci Jawaban\".\n2. Analisis kesamaan makna inti.\n3. Berikan nilai (0-100).\n4. Berikan feedback singkat.\n\nOUTPUT FORMAT (JSON ONLY):\n{\n  \"score\": (integer),\n  \"feedback\": \"(string)\",\n  \"reasoning\": \"(string)\"\n}\n\n Tolong nilai data berikut:\n\n[SOAL]\n{{ $json.body.question_text }}\n\n[KUNCI JAWABAN]\n{{ $json.body.correct_answer }}\n\n[JAWABAN MAHASISWA]\n{{ $json.body.student_answer }}",
        "options": {}
      },
      "type": "@n8n/n8n-nodes-langchain.agent",
      "typeVersion": 3,
      "position": [
        144,
        0
      ],
      "id": "1408442c-9931-4873-a354-e086d257e384",
      "name": "AI Agent"
    },
    {
      "parameters": {
        "jsCode": "// Kita ambil teks output dari AI Agent\n// Pastikan output AI lu formatnya murni JSON kayak contoh lu sebelumnya\nconst aiResponse = items[0].json.output || items[0].json.text;\n\n// Kita ubah teks itu jadi Object (Data matang)\nconst data = JSON.parse(aiResponse);\n\nreturn [\n  {\n    json: {\n      ai_score: data.score,\n      ai_feedback: data.feedback,\n      ai_reasoning: data.reasoning,\n      // Kita panggil lagi ID submission dari Webhook di awal biar gak hilang\n      submission_id: $('Webhook').first().json.body.submission_id\n      // ^ NOTE: Sesuaikan 'body.record.id' dengan struktur JSON webhook lu\n    }\n  }\n];"
      },
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        496,
        0
      ],
      "id": "87a2e1b5-da28-48d5-9e3b-ccaccaf675c8",
      "name": "Code in JavaScript"
    },
    {
      "parameters": {
        "useCustomSchema": true,
        "tableId": "grades",
        "dataToSend": "autoMapInputData"
      },
      "type": "n8n-nodes-base.supabase",
      "typeVersion": 1,
      "position": [
        704,
        0
      ],
      "id": "48031d43-6fdf-45c4-858b-07a5127e6fa4",
      "name": "Create a row",
      "credentials": {
        "supabaseApi": {
          "name": "<your credential>"
        }
      }
    },
    {
      "parameters": {
        "httpMethod": "POST",
        "path": "grade-essay",
        "options": {}
      },
      "type": "n8n-nodes-base.webhook",
      "typeVersion": 2.1,
      "position": [
        -64,
        0
      ],
      "id": "26f8c468-06c5-4bea-bd73-45fc81a1ec2a",
      "name": "Webhook"
    },
    {
      "parameters": {
        "useCustomSchema": true,
        "operation": "update",
        "tableId": "submissions",
        "filters": {
          "conditions": [
            {
              "keyName": "id",
              "condition": "eq",
              "keyValue": "={{ $json.submission_id }}"
            }
          ]
        },
        "fieldsUi": {
          "fieldValues": [
            {
              "fieldId": "status",
              "fieldValue": "graded"
            }
          ]
        }
      },
      "type": "n8n-nodes-base.supabase",
      "typeVersion": 1,
      "position": [
        912,
        0
      ],
      "id": "6729142a-ec4e-4717-9dfb-72041ebfee55",
      "name": "Update a row",
      "credentials": {
        "supabaseApi": {
          "name": "<your credential>"
        }
      }
    }
  ],
  "connections": {
    "OpenAI Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "AI Agent",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "AI Agent": {
      "main": [
        [
          {
            "node": "Code in JavaScript",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Code in JavaScript": {
      "main": [
        [
          {
            "node": "Create a row",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Webhook": {
      "main": [
        [
          {
            "node": "AI Agent",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Create a row": {
      "main": [
        [
          {
            "node": "Update a row",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  },
  "active": false,
  "settings": {
    "executionOrder": "v1"
  },
  "versionId": "310cee07-cb38-44dc-926f-cb82fd708660",
  "meta": {
    "templateCredsSetupCompleted": true
  },
  "id": "pMKrbzEk9TYdeYgG",
  "tags": []
}

Credentials you'll need

Each integration node will prompt for credentials when you import. We strip credential IDs before publishing — you'll add your own.

• openAiApi
• supabaseApi

About this workflow

Ai-Grader. Uses lmChatOpenAi, agent, supabase. Webhook trigger; 6 nodes.

Source: https://github.com/reyvanevan/essay-grader/blob/740ae8ad4fb9453f9b2a76bd6238e8c4a3741c85/ai-grader.json — original creator credit. Request a take-down →

More AI & RAG workflows → · Browse all categories →

Related workflows

Workflows that share integrations, category, or trigger type with this one. All free to copy and import.