Suivi automatique des ventes entrantes

Intermédiaire

Ceci est unLead Nurturing, AI RAG, Multimodal AIworkflow d'automatisation du domainecontenant 12 nœuds.Utilise principalement des nœuds comme Gmail, FormTrigger, Agent, LmChatOpenAi, EmbeddingsOpenAi. Suivi automatique et personnalisé des ventes avec GPT-5, Pinecone et Tavily pour la recherche

Prérequis
  • Compte Google et informations d'identification Gmail API
  • Clé API OpenAI
  • Clé API Pinecone
Aperçu du workflow
Visualisation des connexions entre les nœuds, avec support du zoom et du déplacement
Exporter le workflow
Copiez la configuration JSON suivante dans n8n pour importer et utiliser ce workflow
{
  "id": "JRk4BidOsJmNYCz3",
  "meta": {
    "templateCredsSetupCompleted": true
  },
  "name": "Automatic Inbound Sales Follow Up",
  "tags": [],
  "nodes": [
    {
      "id": "5c469742-7089-4322-9d7f-363d89bc8e84",
      "name": "À la soumission du formulaire",
      "type": "n8n-nodes-base.formTrigger",
      "position": [
        -144,
        0
      ],
      "parameters": {
        "options": {},
        "formTitle": "Business Inquiry",
        "formFields": {
          "values": [
            {
              "fieldLabel": "First Name",
              "requiredField": true
            },
            {
              "fieldLabel": "Last Name",
              "requiredField": true
            },
            {
              "fieldLabel": "Business URL",
              "requiredField": true
            },
            {
              "fieldType": "email",
              "fieldLabel": "Email",
              "requiredField": true
            },
            {
              "fieldType": "number",
              "fieldLabel": "Phone Number (Optional)"
            },
            {
              "fieldLabel": "How can we help you?"
            }
          ]
        },
        "formDescription": "Thank you for your inquiry, we'll get back to you soon!"
      },
      "typeVersion": 2.2
    },
    {
      "id": "530607dd-d303-41a3-94f3-a4c89e4c6a66",
      "name": "Modèle de Chat OpenAI",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        80,
        304
      ],
      "parameters": {
        "model": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-5",
          "cachedResultName": "gpt-5"
        },
        "options": {}
      },
      "typeVersion": 1.2
    },
    {
      "id": "648633b1-b8c2-437f-9384-ce9e9e170675",
      "name": "Mémoire Simple",
      "type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
      "position": [
        272,
        304
      ],
      "parameters": {
        "sessionKey": "={{ $workflow.id }}",
        "sessionIdType": "customKey"
      },
      "typeVersion": 1.3
    },
    {
      "id": "36bf640f-df08-4abd-b7a1-592ef2fff1d2",
      "name": "Analyseur de Sortie Structurée",
      "type": "@n8n/n8n-nodes-langchain.outputParserStructured",
      "position": [
        688,
        288
      ],
      "parameters": {
        "jsonSchemaExample": "{\n\t\"Subject Line\": \"Hello from Purple Unicorn Marketing\",\n\t\"Body\": \"Hey Jake, this is bob from Purpler Unicorn Marketing. Thank you for your inquiry, booking a meeting with me here: www.calendly.com/book-now\"\n}"
      },
      "typeVersion": 1.3
    },
    {
      "id": "1c4e1648-934d-49cc-b645-beb11522ddfe",
      "name": "Gmail",
      "type": "n8n-nodes-base.gmail",
      "position": [
        912,
        0
      ],
      "parameters": {
        "sendTo": "<<<LEAD_EMAIL_PLACEHOLDER>>>",
        "message": "={{ $json.output.Body }}",
        "options": {},
        "subject": "={{ $json.output['Subject Line'] }}",
        "emailType": "text"
      },
      "typeVersion": 2.1
    },
    {
      "id": "6b471a24-6145-47f3-aa19-88aaf1120b63",
      "name": "Note Adhésive",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -240,
        -128
      ],
      "parameters": {
        "width": 260,
        "height": 640,
        "content": "Form Submission Trigger"
      },
      "typeVersion": 1
    },
    {
      "id": "77a38bef-3f32-48f9-9339-b7071fd1fa03",
      "name": "Note Adhésive1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        32,
        -128
      ],
      "parameters": {
        "color": 5,
        "width": 768,
        "height": 640,
        "content": "GPT-5 Inbound Sales Rep Lead Research & Email Writing Agent"
      },
      "typeVersion": 1
    },
    {
      "id": "972490fa-d89c-448b-bc99-62308159833a",
      "name": "Recherche & Rédaction GPT-5",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "position": [
        224,
        0
      ],
      "parameters": {
        "text": "=First Name: {{ $json['First Name'] }}\nLast Name: {{ $json['Last Name'] }}\nBusiness URL: {{ $json['Business URL'] }}\nEmail: {{ $json.Email }}\nPhone Number: {{ $json['Phone Number (Optional)'] }}\nHow Can We Help:{{ $json['How can we help you?'] }}",
        "options": {
          "systemMessage": "You are an effective inbound lead email agent. Your role is to research on the lead's business information and lead's problem statement to craft a personalized email to be sent to the leads with the goal of booking a meeting at www.calendly.com/book-now. Use a friendly tone which is welcoming and easy to read, clear call to action. \n\n#Tool\nUse the Tavily tool to carry out online research that will help your email to the lead.\nUse Pinecone Vector tool to refer to best brand guidelines and outbound practices\n\n##Output\nOutput the email subject line and body in separated JSON Object forma. \n"
        },
        "promptType": "define",
        "hasOutputParser": true
      },
      "typeVersion": 2
    },
    {
      "id": "b288c417-12e7-4c66-82c1-5a9bdb5a10b3",
      "name": "Note Adhésive2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        816,
        -128
      ],
      "parameters": {
        "color": 4,
        "width": 320,
        "height": 640,
        "content": "Send Email Node"
      },
      "typeVersion": 1
    },
    {
      "id": "905eaacd-4e12-44c3-81dc-6af2e784dd6a",
      "name": "Note Adhésive3",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -1328,
        -128
      ],
      "parameters": {
        "color": 2,
        "width": 1072,
        "height": 1776,
        "content": "📧 Automatic Personalized Sales Follow-Up with GPT-5, Pinecone, and Tavily Research\nDescription\n\nNever let a lead go cold. This workflow automatically sends personalized follow-up emails to every inbound inquiry. It combines GPT-5 with Pinecone Vector DB and Tavily research to craft responses that align with your brand’s best practices, tone, and the latest product updates. Using embedded research tools, the workflow ensures each email is both timely and relevant—helping your sales team convert more leads without manual effort.\n\n👉 Watch step-by-step build of workflows like these on: www.youtube.com/@automatewithmarc\n\nHow It Works\n\nForm Trigger – Captures inbound lead details (name, business, email, and message).\n\nAI Sales Agent (GPT-5) – Researches the lead’s business and problem statement, while referencing Pinecone for brand guidelines and product updates. Tavily research is used to enrich responses with the latest context.\n\nStructured Output Parser – Ensures the subject line and email body are generated in a clean JSON format.\n\nGmail Node (Send Follow-Up Email) – Sends a polished, ready-to-go follow-up email to the lead.\n\nSimple Memory – Maintains continuity across follow-ups for a more natural conversation.\n\nWhy Sales Teams Will Love It\n\n⏱ Faster responses — no waiting, leads get an immediate follow-up.\n\n📝 On-brand every time — Pinecone ensures tone matches your sales playbook.\n\n🌍 Research-driven — Tavily provides real-time enrichment for context-aware emails.\n\n📈 Improves conversions — timely, personalized outreach increases meeting bookings.\n\n🤖 Hands-off automation — sales reps can focus on closing, not chasing.\n\nSetup Instructions\n\nForm Trigger – Configure your inbound form to capture lead details (name, email, company, message). Connect it to this workflow.\n\nPinecone Setup\n\nCreate a Pinecone index and embed your brand guidelines, sales playbook, and product updates.\n\nUpdate the Pinecone Vector Store node with your index name.\n\nTavily Setup\n\nAdd your Tavily API key to the Perplexity/Tavily tool node.\n\nOpenAI Setup\n\nAdd your OpenAI API key to the GPT-5 Chat Model node.\n\nAdjust system prompts in the AI Agent node to reflect your company’s style.\n\nGmail Node\n\nConnect your Gmail account to the “Send Follow-Up Email” node.\n\nUpdate sender details if you want the email to come from a shared inbox or a rep’s account.\n\nCustomization\n\nAdjust the system prompt inside the AI Agent to fit your tone (e.g., more casual vs. professional).\n\nUpdate the meeting link (currently Calendly) to your own scheduling tool.\n\nAdd or remove form fields depending on the information you collect from leads.\n\nRequirements\n\nGmail account (for sending follow-up emails)\n\nOpenAI API key (GPT-5)\n\nPinecone account (to store/retrieve style guidelines + product updates)\n\nTavily API key (for online research enrichment)\n\nThis version:\n\n✅ Includes all key tools in the title (GPT-5, Pinecone, Tavily).\n\n✅ Uses Markdown H2 headers.\n\n✅ Provides step-by-step setup instructions.\n\n✅ Adds customization guidance.\n\n✅ Fixes grammar/typos (“GPT-5”, “format”).\n\n✅ Suggests renaming nodes like Gmail → Send Follow-Up Email and Embeddings OpenAI → Pinecone Embeddings for clarity."
      },
      "typeVersion": 1
    },
    {
      "id": "6d481c50-b1d6-409e-8878-bb53cee8e86c",
      "name": "Vector Store Pinecone",
      "type": "@n8n/n8n-nodes-langchain.vectorStorePinecone",
      "position": [
        400,
        240
      ],
      "parameters": {
        "mode": "retrieve-as-tool",
        "options": {},
        "pineconeIndex": {
          "__rl": true,
          "mode": "list",
          "value": "<<<PINECONE_INDEX>>>",
          "cachedResultName": "<<<PINECONE_INDEX_NAME>>>"
        },
        "toolDescription": "Use this tool to refer to writing style, latest product updates."
      },
      "typeVersion": 1.3
    },
    {
      "id": "ef01e62f-b18b-4dad-9222-a229eb1b913a",
      "name": "Embeddings OpenAI",
      "type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
      "position": [
        480,
        384
      ],
      "parameters": {
        "options": {}
      },
      "typeVersion": 1.2
    }
  ],
  "active": false,
  "settings": {
    "executionOrder": "v1"
  },
  "connections": {
    "648633b1-b8c2-437f-9384-ce9e9e170675": {
      "ai_memory": [
        [
          {
            "node": "972490fa-d89c-448b-bc99-62308159833a",
            "type": "ai_memory",
            "index": 0
          }
        ]
      ]
    },
    "ef01e62f-b18b-4dad-9222-a229eb1b913a": {
      "ai_embedding": [
        [
          {
            "node": "6d481c50-b1d6-409e-8878-bb53cee8e86c",
            "type": "ai_embedding",
            "index": 0
          }
        ]
      ]
    },
    "530607dd-d303-41a3-94f3-a4c89e4c6a66": {
      "ai_languageModel": [
        [
          {
            "node": "972490fa-d89c-448b-bc99-62308159833a",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "5c469742-7089-4322-9d7f-363d89bc8e84": {
      "main": [
        [
          {
            "node": "972490fa-d89c-448b-bc99-62308159833a",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "6d481c50-b1d6-409e-8878-bb53cee8e86c": {
      "ai_tool": [
        [
          {
            "node": "972490fa-d89c-448b-bc99-62308159833a",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "36bf640f-df08-4abd-b7a1-592ef2fff1d2": {
      "ai_outputParser": [
        [
          {
            "node": "972490fa-d89c-448b-bc99-62308159833a",
            "type": "ai_outputParser",
            "index": 0
          }
        ]
      ]
    },
    "972490fa-d89c-448b-bc99-62308159833a": {
      "main": [
        [
          {
            "node": "1c4e1648-934d-49cc-b645-beb11522ddfe",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}
Foire aux questions

Comment utiliser ce workflow ?

Copiez le code de configuration JSON ci-dessus, créez un nouveau workflow dans votre instance n8n et sélectionnez "Importer depuis le JSON", collez la configuration et modifiez les paramètres d'authentification selon vos besoins.

Dans quelles scénarios ce workflow est-il adapté ?

Intermédiaire - Nurturing de leads, RAG IA, IA Multimodale

Est-ce payant ?

Ce workflow est entièrement gratuit et peut être utilisé directement. Veuillez noter que les services tiers utilisés dans le workflow (comme l'API OpenAI) peuvent nécessiter un paiement de votre part.

Informations sur le workflow
Niveau de difficulté
Intermédiaire
Nombre de nœuds12
Catégorie3
Types de nœuds9
Description de la difficulté

Adapté aux utilisateurs expérimentés, avec des workflows de complexité moyenne contenant 6-15 nœuds

Auteur
Automate With Marc

Automate With Marc

@marconi

Automating Start-Up and Business processes. Helping non-techies understand and leverage Agentic AI with easy to understand step-by-step tutorials. Check out my educational content: https://www.youtube.com/@Automatewithmarc

Liens externes
Voir sur n8n.io

Partager ce workflow

Catégories

Catégories: 34