Workflow Email Marketing AI

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 →

{
  "nodes": [
    {
      "parameters": {},
      "id": "start-node",
      "name": "Manual Trigger",
      "type": "n8n-nodes-base.manualTrigger",
      "typeVersion": 1,
      "position": [
        240,
        300
      ]
    },
    {
      "parameters": {
        "filePath": "/tmp/entreprises.csv",
        "options": {}
      },
      "id": "read-csv",
      "name": "Read Binary File",
      "type": "n8n-nodes-base.readBinaryFile",
      "typeVersion": 1,
      "position": [
        440,
        300
      ]
    },
    {
      "parameters": {
        "jsCode": "// Parse CSV to JSON\n// Get binary data from the previous node\nconst binaryData = $input.first().binary;\nlet csvText;\n\n// Check if binary data exists and get the data\nif (binaryData && binaryData.data) {\n  // If data is base64 encoded\n  csvText = Buffer.from(binaryData.data.data, 'base64').toString('utf-8');\n} else {\n  throw new Error('No binary data found. Make sure the Read Binary File node is properly configured.');\n}\n\n// Simple CSV parser\nconst lines = csvText.trim().split('\\n');\nif (lines.length < 2) {\n  throw new Error('CSV file must have at least a header and one data row.');\n}\n\nconst headers = lines[0].split(',').map(h => h.replace(/\"/g, '').trim());\nconsole.log('CSV Headers:', headers);\n\nconst items = [];\nfor (let i = 1; i < lines.length; i++) {\n  if (lines[i].trim() === '') continue; // Skip empty lines\n  \n  const values = lines[i].split(',').map(v => v.replace(/\"/g, '').trim());\n  const item = {};\n  \n  headers.forEach((header, index) => {\n    item[header] = values[index] || '';\n  });\n  \n  items.push({\n    json: item\n  });\n}\n\nconsole.log(`\u2705 Parsed ${items.length} companies from CSV`);\nconsole.log('First item example:', items[0]);\nreturn items;"
      },
      "id": "parse-csv",
      "name": "Parse CSV",
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        640,
        300
      ]
    },
    {
      "parameters": {
        "batchSize": 1,
        "options": {
          "reset": false
        }
      },
      "id": "split-batches",
      "name": "Split in Batches",
      "type": "n8n-nodes-base.splitInBatches",
      "typeVersion": 3,
      "position": [
        840,
        300
      ]
    },
    {
      "parameters": {
        "resource": "{{ $vars.AZURE_OPENAI_RESOURCE }}",
        "apiVersion": "2024-02-15-preview",
        "deploymentId": "gpt-4",
        "options": {
          "temperature": 0.7,
          "maxTokens": 1500
        }
      },
      "id": "azure-openai",
      "name": "Azure OpenAI Chat Model",
      "type": "@n8n/n8n-nodes-langchain.lmChatAzureOpenAi",
      "typeVersion": 1,
      "position": [
        1040,
        200
      ],
      "credentials": {
        "azureOpenAiApi": {
          "name": "<your credential>"
        }
      }
    },
    {
      "parameters": {
        "agent": "toolsAgent",
        "systemMessage": "Tu es un expert en r\u00e9daction d'emails marketing personnalis\u00e9s en fran\u00e7ais. Tu cr\u00e9es des emails professionnels, engageants et personnalis\u00e9s pour chaque entreprise.\n\nTon objectif est de :\n1. Cr\u00e9er un email personnalis\u00e9 et professionnel\n2. Utiliser les informations sp\u00e9cifiques de l'entreprise\n3. Adapter le ton selon le secteur d'activit\u00e9\n4. Inclure un call-to-action clair\n5. Garder un style chaleureux mais professionnel\n\nFormat de r\u00e9ponse OBLIGATOIRE :\nOBJET: [Sujet accrocheur personnalis\u00e9]\n\nCORPS:\n[Email complet en HTML avec personnalisation]",
        "text": "Cr\u00e9e un email marketing personnalis\u00e9 pour cette entreprise :\n\n**Informations de l'entreprise :**\n- Nom de l'entreprise: {{ $json.nom_entreprise }}\n- Secteur d'activit\u00e9: {{ $json.secteur }}\n- Contact: {{ $json.nom_contact }}\n- Email: {{ $json.email }}\n- Taille entreprise: {{ $json.taille }}\n- Ville: {{ $json.ville }}\n- T\u00e9l\u00e9phone: {{ $json.telephone }}\n\n**Instructions sp\u00e9cifiques :**\n1. Adresse-toi personnellement \u00e0 {{ $json.nom_contact }}\n2. Mentionne sp\u00e9cifiquement leur secteur \"{{ $json.secteur }}\"\n3. Adapte la proposition \u00e0 leur taille d'entreprise \"{{ $json.taille }}\"\n4. Mentionne leur localisation \"{{ $json.ville }}\"\n5. Propose nos services d'automatisation n8n adapt\u00e9s \u00e0 leur besoin\n6. Inclus un call-to-action pour programmer un appel de 30 minutes\n7. Utilise un ton professionnel mais chaleureux\n8. Email en fran\u00e7ais avec du HTML propre\n\nCr\u00e9e maintenant l'email complet !",
        "options": {
          "maxIterations": 3
        }
      },
      "id": "ai-agent",
      "name": "AI Agent",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "typeVersion": 1,
      "position": [
        1040,
        300
      ]
    },
    {
      "parameters": {
        "jsCode": "// Extract subject and body from AI response\nconst aiResponse = $input.first().json.output;\nlet subject = '';\nlet body = '';\n\n// Parse the AI response to extract OBJET and CORPS\nif (aiResponse.includes('OBJET:')) {\n  const subjectMatch = aiResponse.match(/OBJET:\\s*(.+?)(?=\\n\\nCORPS:|$)/s);\n  if (subjectMatch) {\n    subject = subjectMatch[1].trim();\n  }\n}\n\nif (aiResponse.includes('CORPS:')) {\n  const bodyMatch = aiResponse.match(/CORPS:\\s*([\\s\\S]+?)$/s);\n  if (bodyMatch) {\n    body = bodyMatch[1].trim();\n  }\n} else {\n  // Fallback: use the whole response as body if format is different\n  body = aiResponse;\n}\n\n// Ensure we have content\nif (!subject) {\n  subject = `Proposition personnalis\u00e9e pour ${$('Split in Batches').item.json.nom_entreprise}`;\n}\n\nif (!body) {\n  body = aiResponse;\n}\n\n// Return the parsed data along with recipient info\nreturn [{\n  json: {\n    subject: subject,\n    body: body,\n    recipientEmail: $('Split in Batches').item.json.email,\n    recipientName: $('Split in Batches').item.json.nom_contact,\n    companyName: $('Split in Batches').item.json.nom_entreprise,\n    sector: $('Split in Batches').item.json.secteur\n  }\n}];"
      },
      "id": "extract-email",
      "name": "Extract Email Content",
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        1240,
        300
      ]
    },
    {
      "parameters": {
        "fromEmail": "{{ $vars.PRIVATE_EMAIL_USER }}",
        "toEmail": "{{ $json.recipientEmail }}",
        "subject": "{{ $json.subject }}",
        "emailType": "html",
        "message": "{{ $json.body }}",
        "options": {
          "replyTo": "{{ $vars.PRIVATE_EMAIL_USER }}",
          "priority": "normal"
        }
      },
      "id": "send-email",
      "name": "Send Email",
      "type": "n8n-nodes-base.emailSend",
      "typeVersion": 2,
      "position": [
        1440,
        300
      ],
      "credentials": {
        "smtp": {
          "name": "<your credential>"
        }
      }
    },
    {
      "parameters": {
        "amount": 5,
        "unit": "seconds"
      },
      "id": "wait-node",
      "name": "Wait 5 seconds",
      "type": "n8n-nodes-base.wait",
      "typeVersion": 1,
      "position": [
        1640,
        300
      ]
    },
    {
      "parameters": {
        "jsCode": "// Log the email sending result\nconst emailData = $input.first().json;\nconst recipientData = $('Extract Email Content').first().json;\n\nconsole.log(`\u2705 Email envoy\u00e9 avec succ\u00e8s \u00e0:`);\nconsole.log(`\ud83d\udce7 Destinataire: ${recipientData.recipientName} (${recipientData.recipientEmail})`);\nconsole.log(`\ud83c\udfe2 Entreprise: ${recipientData.companyName}`);\nconsole.log(`\ud83d\udcdd Sujet: ${recipientData.subject}`);\nconsole.log(`\u23f0 Heure d'envoi: ${new Date().toLocaleString('fr-FR')}`);\nconsole.log('---');\n\nreturn [{\n  json: {\n    status: 'success',\n    recipient: recipientData.recipientEmail,\n    company: recipientData.companyName,\n    subject: recipientData.subject,\n    sentAt: new Date().toISOString(),\n    message: `Email envoy\u00e9 avec succ\u00e8s \u00e0 ${recipientData.recipientName} de ${recipientData.companyName}`\n  }\n}];"
      },
      "id": "log-success",
      "name": "Log Success",
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        1840,
        300
      ]
    }
  ],
  "connections": {
    "Manual Trigger": {
      "main": [
        [
          {
            "node": "Read Binary File",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Read Binary File": {
      "main": [
        [
          {
            "node": "Parse CSV",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Parse CSV": {
      "main": [
        [
          {
            "node": "Split in Batches",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Split in Batches": {
      "main": [
        [
          {
            "node": "AI Agent",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Azure OpenAI Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "AI Agent",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "AI Agent": {
      "main": [
        [
          {
            "node": "Extract Email Content",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Extract Email Content": {
      "main": [
        [
          {
            "node": "Send Email",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Send Email": {
      "main": [
        [
          {
            "node": "Wait 5 seconds",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Wait 5 seconds": {
      "main": [
        [
          {
            "node": "Log Success",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Log Success": {
      "main": [
        [
          {
            "node": "Split in Batches",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  },
  "settings": {
    "executionOrder": "v1"
  },
  "staticData": null,
  "tags": [
    {
      "createdAt": "2024-01-15T10:00:00.000Z",
      "updatedAt": "2024-01-15T10:00:00.000Z",
      "id": "email-marketing",
      "name": "Email Marketing"
    },
    {
      "createdAt": "2024-01-15T10:00:00.000Z",
      "updatedAt": "2024-01-15T10:00:00.000Z",
      "id": "ai-automation",
      "name": "AI Automation"
    }
  ],
  "triggerCount": 1,
  "updatedAt": "2024-01-15T10:00:00.000Z",
  "versionId": "1"
}

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.

• azureOpenAiApi
• smtp

About this workflow

Workflow Email Marketing Ai. Uses readBinaryFile, lmChatAzureOpenAi, agent, emailSend. Event-driven trigger; 10 nodes.

Source: https://github.com/WizzyDev997/N8N/blob/6f91f33c272255d142e6f57af41b08e6199e352f/workflow_email_marketing_ai.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.