← Retour aux workflows
Workflow n8n

Automatisation Gmail avec n8n : création d'emails de vente

  • Ce workflow n8n a pour objectif d'automatiser la création d'emails de vente à partir des données clients récupérées dans Gmail et HubSpot. Il est particulièrement utile pour les équipes commerciales qui souhaitent gagner du temps dans la rédaction d'emails personnalisés et améliorer leur efficacité. Grâce à cette automatisation n8n, les utilisateurs peuvent générer des emails de vente en utilisant des modèles de langage avancés comme Google Gemini, tout en intégrant des notes et des informations pertinentes sur les clients.
  • Le déroulé du workflow commence par un déclencheur manuel, permettant à l'utilisateur de tester le flux à tout moment. Ensuite, des variables sont définies pour stocker les informations nécessaires. Les modèles de langage Google Gemini sont utilisés pour analyser les données et générer des emails de vente adaptés. Par la suite, des notes autocollantes sont créées pour visualiser les informations clés. Les correspondances des clients sont récupérées via Gmail, et les contacts sont extraits de HubSpot pour alimenter le processus. Chaque contact est ensuite traité individuellement pour générer un email de vente personnalisé.
  • Les bénéfices de ce workflow incluent une réduction significative du temps passé à rédiger des emails, une personnalisation accrue des messages envoyés aux clients, et une meilleure organisation des informations clients. En intégrant cette automatisation dans leur processus, les équipes commerciales peuvent se concentrer sur des tâches à plus forte valeur ajoutée, tout en améliorant leur taux de conversion.
Tags clés :automatisationGmailHubSpotn8nemail marketing
🎯Pour qui ?🧩Problème résolu📋Étapes du flux🛠Guide de personnalisation
Catégorie: Manual · Tags: automatisation, Gmail, HubSpot, n8n, email marketing❤ 0

Workflow n8n Gmail, HubSpot, email marketing : vue d'ensemble

Schéma des nœuds et connexions de ce workflow n8n, généré à partir du JSON n8n.

React Flow
Besoin d'aide ?

Workflow n8n Gmail, HubSpot, email marketing : détail des nœuds

  • When clicking ‘Test workflow’

    Déclenche le workflow lorsque l'utilisateur clique sur 'Test workflow'.

  • Variables

    Définit des variables à utiliser dans le workflow.

  • Google Gemini Chat Model

    Utilise le modèle de chat Google Gemini pour générer des réponses.

  • Google Gemini Chat Model1

    Utilise un second modèle de chat Google Gemini pour générer des réponses.

  • Create Draft Email For Review

    Crée un brouillon d'email pour révision dans Gmail.

  • Generate Sales Email

    Génère un email de vente à partir des informations fournies.

  • Sticky Note

    Crée une note autocollante avec les paramètres spécifiés.

  • Sticky Note1

    Crée une seconde note autocollante avec les paramètres spécifiés.

  • Sticky Note2

    Crée une troisième note autocollante avec les paramètres spécifiés.

  • Sticky Note3

    Crée une quatrième note autocollante avec les paramètres spécifiés.

  • Analyse and Build Persona

    Analyse le texte et construit un persona à partir des informations fournies.

  • Sticky Note4

    Crée une cinquième note autocollante avec les paramètres spécifiés.

  • Get All Customer's Correspondence

    Récupère toute la correspondance d'un client dans Gmail.

  • Get Contacts

    Récupère les contacts depuis HubSpot selon les critères spécifiés.

  • For Each Contact

    Divise les contacts récupérés en plusieurs lots pour traitement.

  • Contact Ref

    Noeud sans opération spécifique, utilisé pour le passage de données.

  • Sticky Note5

    Crée une sixième note autocollante avec les paramètres spécifiés.

Inscris-toi pour voir l'intégralité du workflow

Inscription gratuite

S'inscrire gratuitementBesoin d'aide ?
{
  "meta": {
    "instanceId": "408f9fb9940c3cb18ffdef0e0150fe342d6e655c3a9fac21f0f644e8bedabcd9",
    "templateCredsSetupCompleted": true
  },
  "nodes": [
    {
      "id": "93a8b03f-ff6b-4559-9cb1-9f439ff5e990",
      "name": "When clicking ‘Test workflow’",
      "type": "n8n-nodes-base.manualTrigger",
      "position": [
        -1180,
        0
      ],
      "parameters": {},
      "typeVersion": 1
    },
    {
      "id": "0aed449c-c60a-4309-91d2-4db9ed1f4ad2",
      "name": "Variables",
      "type": "n8n-nodes-base.set",
      "position": [
        -120,
        0
      ],
      "parameters": {
        "options": {},
        "assignments": {
          "assignments": [
            {
              "id": "a6c47778-33f4-46a3-a86a-fd1e75930d93",
              "name": "firstname",
              "type": "string",
              "value": "={{ $json.properties.firstname }}"
            },
            {
              "id": "0e50b2bc-4bea-4fd0-95c0-46a87da69c19",
              "name": "lastname",
              "type": "string",
              "value": "={{ $json.properties.lastname }}"
            },
            {
              "id": "ee15f298-77f6-4c4a-b03b-c2cf9a53bdc2",
              "name": "email",
              "type": "string",
              "value": "={{ $json.properties.email }}"
            },
            {
              "id": "98a718f5-4372-4282-8a9a-46f2af39677a",
              "name": "product_to_sell",
              "type": "string",
              "value": "=AI partnerships: a consulting package of AI development and services. We help customers find a strong foothold on AI initiatives bringing them to life cost effectively and always with results."
            }
          ]
        }
      },
      "typeVersion": 3.4
    },
    {
      "id": "f21c0147-dd18-4b06-9f58-258b8946977d",
      "name": "Google Gemini Chat Model",
      "type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
      "position": [
        520,
        160
      ],
      "parameters": {
        "options": {},
        "modelName": "models/gemini-2.0-flash"
      },
      "credentials": {
        "googlePalmApi": {
          "id": "dSxo6ns5wn658r8N",
          "name": "Google Gemini(PaLM) Api account"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "27aaa070-4de5-479a-83eb-d2e0810a19da",
      "name": "Google Gemini Chat Model1",
      "type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
      "position": [
        1120,
        160
      ],
      "parameters": {
        "options": {},
        "modelName": "models/gemini-2.0-flash"
      },
      "credentials": {
        "googlePalmApi": {
          "id": "dSxo6ns5wn658r8N",
          "name": "Google Gemini(PaLM) Api account"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "b76ec237-3d90-4ed4-8746-36693775a39f",
      "name": "Create Draft Email For Review",
      "type": "n8n-nodes-base.gmail",
      "position": [
        1680,
        180
      ],
      "webhookId": "8b3d78e5-8cea-4205-a9db-c66ec01f9558",
      "parameters": {
        "message": "={{ $json.output.body }}",
        "options": {
          "sendTo": "={{ $('Variables').first().json.email }}"
        },
        "subject": "={{ $json.output.subject }}",
        "resource": "draft",
        "emailType": "html"
      },
      "credentials": {
        "gmailOAuth2": {
          "id": "Sf5Gfl9NiFTNXFWb",
          "name": "Gmail account"
        }
      },
      "typeVersion": 2.1
    },
    {
      "id": "7d62abe5-9278-45f2-ba07-aba0f4353a00",
      "name": "Generate Sales Email",
      "type": "@n8n/n8n-nodes-langchain.informationExtractor",
      "position": [
        1040,
        0
      ],
      "parameters": {
        "text": "=# Profile of {{ $('Variables').first().json.firstname }} {{ $('Variables').first().json.lastname }}\n{{ Object.keys($json.output).map(key => `## ${key}\\n${$json.output[key]}`).join('\\n') }}",
        "options": {
          "systemPromptTemplate": "=You are a sales representative drafting an email to close a potential customer on the following product: <product>{{ $('Variables').first().json.product_to_sell }}</product>\n\nUse the provided profile to draft the a suitable email which reflects similar communication style and addresses their values, ultimately convinces the customer to inquire about and/or buy this product. Provide only the subject and body of the message as this text will go into a template. Omit the subject and signature."
        },
        "attributes": {
          "attributes": [
            {
              "name": "subject",
              "required": true,
              "description": "the subject of the message"
            },
            {
              "name": "body",
              "required": true,
              "description": "the body of the message with html styling"
            }
          ]
        }
      },
      "typeVersion": 1
    },
    {
      "id": "71cd4b52-c3cd-413e-b495-f0ef511af9b1",
      "name": "Sticky Note",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -220,
        -200
      ],
      "parameters": {
        "color": 7,
        "width": 520,
        "height": 420,
        "content": "## 2. Research Customer via Emails\nEmails can be a great source of research on how a customer or potential customer thinks, behaves and communicates. This template does require some interaction beforehand but this should could be shared amongst colleagues or a CRM."
      },
      "typeVersion": 1
    },
    {
      "id": "f3cb9e8d-8d67-42a2-a9cd-7aae93a23816",
      "name": "Sticky Note1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        320,
        -200
      ],
      "parameters": {
        "color": 7,
        "width": 540,
        "height": 540,
        "content": "## 3. Build Persona Outline from Research\nOnce we gather all the emails, we can use AI to analyse and construct a quick persona on our customer. Personas are useful to understand the customer's position and how favourably they might respond to a product and/or service. The Information Extractor node is used to guide the LLM for attributes we're interested in."
      },
      "typeVersion": 1
    },
    {
      "id": "e0bdca91-e744-4717-ada6-5991e2d6c054",
      "name": "Sticky Note2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        880,
        -200
      ],
      "parameters": {
        "color": 7,
        "width": 560,
        "height": 540,
        "content": "## 4. Generate Sales Pitch based on Persona\nUsing the persona, we can again ask AI to generate the perfect sales email which takes into consideration the customer's beliefs, values and communication style. In this way, each sales email can be carefully written to improve its appeal to the customer."
      },
      "typeVersion": 1
    },
    {
      "id": "68be2c2c-5006-4041-b8ed-8c6b26d37251",
      "name": "Sticky Note3",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1480,
        -40
      ],
      "parameters": {
        "color": 7,
        "width": 480,
        "height": 440,
        "content": "## 5. Create Draft for Human Review\nFinally, an email draft is created to store the generated sales pitch for human review. If given, a list of customers to target, a SDR can ensure customised outreach in minutes rather than hours or days. "
      },
      "typeVersion": 1
    },
    {
      "id": "893d42c3-c5fc-4cc3-acd2-5d847d4ebf1a",
      "name": "Analyse and Build Persona",
      "type": "@n8n/n8n-nodes-langchain.informationExtractor",
      "position": [
        440,
        0
      ],
      "parameters": {
        "text": "={{\n$input.all()\n  .map(item => `subject: ${item.json.subject}\ndate: ${$json.headers.date}\nmessage: ${item.json.text.substr(0, item.json.text.indexOf('> wrote:') ?? item.json.text.length).replace(/^On[\\w\\W]+$/im, '')}`\n  ).join('\\n---\\n')\n}}",
        "options": {
          "systemPromptTemplate": "=Your task is to build a persona of a customer or potential customer so that we may better serve them for our business. Analyse the recent correspondence of the user, {{ $('Variables').item.json.email }}, and extract the required attributes."
        },
        "attributes": {
          "attributes": [
            {
              "name": "decision_making_style",
              "required": true,
              "description": "=Analytical vs. Intuitive: Do they rely on data or gut feelings?\n\nRisk Appetite: Conservative, calculated risk-taker, or bold?\n\nSpeed of Decision-Making: Quick and assertive or deliberate and methodical?"
            },
            {
              "name": " communication_preferences",
              "required": true,
              "description": "=Preferred Medium: Email, phone calls, in-person meetings, messaging apps?\n\nDetail Orientation: High-level summaries or deep-dive explanations?\n\nTone & Formality: Casual vs. professional, direct vs. diplomatic?"
            },
            {
              "name": "pain_points_challenges",
              "required": true,
              "description": "=Current Business Challenges: What problems are they actively trying to solve?\n\nIndustry Pressures: Competitive landscape, economic concerns, regulatory issues?\n\nOperational Bottlenecks: Efficiency, team structure, technology gaps?"
            },
            {
              "name": "professional_goals_motivations",
              "required": true,
              "description": "=Personal Career Goals: Promotion, recognition, financial growth, legacy-building?\n\nBusiness Priorities: Revenue growth, innovation, market expansion, cost reduction?\n\nKey Performance Indicators (KPIs): How do they measure success?"
            },
            {
              "name": "work_style_preferences",
              "required": true,
              "description": "=Collaboration vs. Independence: Do they prefer teamwork or autonomy?\n\nLevel of Involvement: Hands-on or delegate-and-review?\n\nResponse Time Expectation: Do they expect immediate follow-ups or are they flexible?"
            },
            {
              "name": "personality_behavioral_traits",
              "required": true,
              "description": "=Big Five Traits: Are they open to new ideas, structured, agreeable, extroverted?\n\nConflict Resolution Style: Do they avoid, confront, or negotiate?\n\nTrust-Building Factors: Do they value reliability, transparency, exclusivity?"
            },
            {
              "name": " buying_investment_behavior",
              "required": true,
              "description": "=Budget Sensitivity: Price-conscious or value-focused?\n\nBrand Loyalty vs. Openness: Do they stick with familiar providers or explore new options?\n\nDecision Influencers: Do they rely on peers, market research, gut instinct?"
            },
            {
              "name": "preferred_business_culture_ethics",
              "required": true,
              "description": "=Formality vs. Informality: Corporate structure vs. entrepreneurial mindset?\n\nCore Values: Integrity, innovation, customer-first, sustainability?\n\nCultural Sensitivity: Are there cultural nuances to be aware of in their decision-making?"
            },
            {
              "name": "industry_competitive_awareness",
              "required": true,
              "description": "=Market Trends Interest: Do they actively track industry shifts?\n\nCompetitor Awareness: Are they reactive to competitors, or focused on internal growth?\n\nTech Adoption: Do they embrace innovation, or are they slow adopters?"
            }
          ]
        }
      },
      "executeOnce": true,
      "typeVersion": 1
    },
    {
      "id": "f27b7b8d-e9e8-445c-9209-25323bb40db4",
      "name": "Sticky Note4",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -1400,
        -860
      ],
      "parameters": {
        "width": 480,
        "height": 1080,
        "content": "## Try it out\n### This n8n template uses existing emails from customers as context to customise and \"finetune\" outreach emails to them using AI.\n\nBy now, it should be common knowledge that we can leverage AI to generate unique emails but in a way, they can remain generic as the AI lacks the customer context to be truly personalised. One way to solve this is \n\n### How it works\n* Customers to target are pulled from Hubspot and each customer is then run in a loop. We're using a loop as the retrieved emails for each customer become separate items and a loop helps with item reference.\n* We connect to our Gmail account to pull all emails recieved from the customer.\n* The contents of the email will be suitable to build a short persona of the customer. We use the Information Extractor to get our AI model to pull out the key attributes of this persona such as decision making style and communication preferences.\n* With this persona, we can now pass this to our AI model to generate a personalised outreach email specifically for our customer.\n* Finally, a draft email is created for human review before sending. If you would rather send the email straight away, this is also possible.\n\n### How to use\n* Define the topic of the outreach email in the \"variables\" node. This directs the AI on what outreach email to generate.\n* Ensure the emails are pulled from the right account. If emails may contain sensitive data, adjust the filters and text parsing to ensure these are not leaked to the AI (which might then leak into the generated email).\n\n### Need Help?\nJoin the [Discord](https://discord.com/invite/XPKeKXeB7d) or ask in the [Forum](https://community.n8n.io/)!\n\nHappy Hacking!"
      },
      "typeVersion": 1
    },
    {
      "id": "72efcdea-3429-44e0-a29c-8ae0144783ae",
      "name": "Get All Customer's Correspondence",
      "type": "n8n-nodes-base.gmail",
      "position": [
        80,
        0
      ],
      "webhookId": "4d8c4b7a-da0b-49aa-bda8-7b1d89c62636",
      "parameters": {
        "limit": 20,
        "simple": false,
        "filters": {
          "q": "=from:{{ $json.email }}"
        },
        "options": {},
        "operation": "getAll"
      },
      "credentials": {
        "gmailOAuth2": {
          "id": "Sf5Gfl9NiFTNXFWb",
          "name": "Gmail account"
        }
      },
      "typeVersion": 2.1
    },
    {
      "id": "e73c8a55-c85f-45a1-9735-1cea61caff3e",
      "name": "Get Contacts",
      "type": "n8n-nodes-base.hubspot",
      "position": [
        -820,
        0
      ],
      "parameters": {
        "operation": "search",
        "authentication": "appToken",
        "filterGroupsUi": {
          "filterGroupsValues": [
            {
              "filtersUi": {
                "filterValues": [
                  {
                    "value": "DECISION_MAKER",
                    "propertyName": "hs_buying_role|enumeration"
                  }
                ]
              }
            }
          ]
        },
        "additionalFields": {}
      },
      "credentials": {
        "hubspotAppToken": {
          "id": "Qhag92BwOPZfXGfz",
          "name": "HubSpot account (Intrigued-Zoo)"
        }
      },
      "typeVersion": 2.1
    },
    {
      "id": "3579a71d-ce1f-4175-9118-87997158dcb6",
      "name": "For Each Contact",
      "type": "n8n-nodes-base.splitInBatches",
      "position": [
        -620,
        0
      ],
      "parameters": {
        "options": {}
      },
      "typeVersion": 3
    },
    {
      "id": "45679613-3114-4742-9e7a-700d8d29eff6",
      "name": "Contact Ref",
      "type": "n8n-nodes-base.noOp",
      "position": [
        -420,
        0
      ],
      "parameters": {},
      "typeVersion": 1
    },
    {
      "id": "18594bbd-efc5-4fbf-8693-ffcdfcfd900f",
      "name": "Sticky Note5",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -880,
        -200
      ],
      "parameters": {
        "color": 7,
        "width": 640,
        "height": 420,
        "content": "## 1. Get Targeted Existing Customers\nAs with all campaigns, it's good to have a targeted subset of customers to aim for to assess the response. Here, we can pull them out of a CRM like Hubspot if granular filtering is required for example but even a simple csv of contacts would also work."
      },
      "typeVersion": 1
    }
  ],
  "pinData": {},
  "connections": {
    "Variables": {
      "main": [
        [
          {
            "node": "Get All Customer's Correspondence",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Contact Ref": {
      "main": [
        [
          {
            "node": "Variables",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Get Contacts": {
      "main": [
        [
          {
            "node": "For Each Contact",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "For Each Contact": {
      "main": [
        [],
        [
          {
            "node": "Contact Ref",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Generate Sales Email": {
      "main": [
        [
          {
            "node": "Create Draft Email For Review",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Google Gemini Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "Analyse and Build Persona",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Analyse and Build Persona": {
      "main": [
        [
          {
            "node": "Generate Sales Email",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Google Gemini Chat Model1": {
      "ai_languageModel": [
        [
          {
            "node": "Generate Sales Email",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Create Draft Email For Review": {
      "main": [
        [
          {
            "node": "For Each Contact",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Get All Customer's Correspondence": {
      "main": [
        [
          {
            "node": "Analyse and Build Persona",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "When clicking ‘Test workflow’": {
      "main": [
        [
          {
            "node": "Get Contacts",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}

Workflow n8n Gmail, HubSpot, email marketing : pour qui est ce workflow ?

Ce workflow s'adresse aux équipes commerciales et marketing des PME et grandes entreprises qui utilisent Gmail et HubSpot pour gérer leurs contacts et leurs communications. Un niveau technique moyen est recommandé pour personnaliser et adapter le workflow à leurs besoins spécifiques.

Workflow n8n Gmail, HubSpot, email marketing : problème résolu

Ce workflow résout le problème de la création manuelle d'emails de vente, qui peut être long et répétitif. En automatisant ce processus, il élimine les frustrations liées à la personnalisation des messages pour chaque client, réduit le risque d'erreurs humaines, et permet aux utilisateurs de gagner un temps précieux. Après mise en place, les utilisateurs peuvent s'attendre à une augmentation de leur productivité et à une amélioration de leur engagement client.

Workflow n8n Gmail, HubSpot, email marketing : étapes du workflow

Étape 1 : Le workflow est déclenché manuellement lorsque l'utilisateur clique sur 'Test workflow'.

  • Étape 1 : Des variables sont définies pour stocker les informations nécessaires à la création des emails.
  • Étape 2 : Les modèles de langage Google Gemini sont utilisés pour analyser les données clients et générer des emails de vente.
  • Étape 3 : Des notes autocollantes sont créées pour visualiser les informations clés.
  • Étape 4 : Les correspondances des clients sont récupérées via Gmail.
  • Étape 5 : Les contacts sont extraits de HubSpot pour alimenter le processus.
  • Étape 6 : Chaque contact est traité individuellement pour générer un email de vente personnalisé.

Workflow n8n Gmail, HubSpot, email marketing : guide de personnalisation

Pour personnaliser ce workflow, les utilisateurs peuvent modifier les paramètres des noeuds, notamment les options de génération d'emails dans les modèles de langage Google Gemini. Ils peuvent également ajuster les filtres de recherche lors de la récupération des correspondances dans Gmail et des contacts dans HubSpot. Il est conseillé de sécuriser le flux en configurant correctement les authentifications pour les services utilisés. Enfin, les utilisateurs peuvent ajouter d'autres outils ou services pour enrichir le workflow selon leurs besoins spécifiques.