Analizar registros de clientes y enrutar retroalimentación con GPT-4o Mini, HubSpot y Gmail

Intermedio

Este es unSales, Support, AI, Marketingflujo de automatización del dominio deautomatización que contiene 14 nodos.Utiliza principalmente nodos como Set, Form, Hubspot, GmailTool, FormTrigger, combinando tecnología de inteligencia artificial para lograr automatización inteligente. Analizar registros de clientes y enrutar retroalimentación con GPT-4o Mini, HubSpot y Gmail

Requisitos previos
  • Clave de API de HubSpot
  • Cuenta de Google y credenciales de API de Gmail
  • Clave de API de OpenAI
Vista previa del flujo de trabajo
Visualización de las conexiones entre nodos, con soporte para zoom y panorámica
Exportar flujo de trabajo
Copie la siguiente configuración JSON en n8n para importar y usar este flujo de trabajo
{
  "nodes": [
    {
      "id": "d681d557-cb02-4fb1-9871-bfae504992ca",
      "name": "HubSpot",
      "type": "n8n-nodes-base.hubspot",
      "notes": "Add meeting notes in the contact form",
      "position": [
        260,
        40
      ],
      "parameters": {
        "type": "meeting",
        "metadata": {
          "body": "={{ $('Summarization').item.json.response.text }}",
          "title": "New meeting"
        },
        "resource": "engagement",
        "authentication": "oAuth2",
        "additionalFields": {
          "associations": {
            "contactIds": "={{ $json.properties.hs_object_id }}"
          }
        }
      },
      "credentials": {
        "hubspotOAuth2Api": {
          "id": "JxzF93M0SJ00jDD9",
          "name": "HubSpot account"
        }
      },
      "notesInFlow": true,
      "typeVersion": 2.1
    },
    {
      "id": "e4849449-3464-4deb-a9be-07b3d0bb2d56",
      "name": "HubSpot1",
      "type": "n8n-nodes-base.hubspot",
      "notes": "Search for the id",
      "position": [
        20,
        40
      ],
      "parameters": {
        "operation": "search",
        "authentication": "oAuth2",
        "filterGroupsUi": {
          "filterGroupsValues": [
            {
              "filtersUi": {
                "filterValues": [
                  {
                    "value": "={{ $('Enter Client Transcript').item.json['client email'] }}",
                    "propertyName": "email|string"
                  }
                ]
              }
            }
          ]
        },
        "additionalFields": {}
      },
      "credentials": {
        "hubspotOAuth2Api": {
          "id": "JxzF93M0SJ00jDD9",
          "name": "HubSpot account"
        }
      },
      "notesInFlow": true,
      "typeVersion": 2.1
    },
    {
      "id": "16ac22b7-62fd-429c-b766-5ffe503a3231",
      "name": "Nota adhesiva",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -60,
        -80
      ],
      "parameters": {
        "color": 4,
        "width": 540,
        "height": 280,
        "content": "## Save the data to Hubspot\n- Search for the client ID based on his email\n- Upload the summarized conversation as meeting notes"
      },
      "typeVersion": 1
    },
    {
      "id": "4f51bfc1-8270-4e04-b395-f4ceed9129a4",
      "name": "Nota adhesiva1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -60,
        220
      ],
      "parameters": {
        "color": 4,
        "width": 540,
        "height": 520,
        "content": "## Router agent\nMakes decisions with the help of an LLM  \n- Analyzes the content\n- Decides which part of the transcript is relevant to the different departments\n- Sends the emails to the departments\n"
      },
      "typeVersion": 1
    },
    {
      "id": "96142f55-cbb4-47e9-a44e-b4f783eeeeb5",
      "name": "Agente de enrutamiento",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "notes": "Route the client feedback topics to the relevant department ",
      "position": [
        20,
        420
      ],
      "parameters": {
        "text": "={{ $('Enter Client Transcript').item.json['client conversation'] }}",
        "options": {
          "systemMessage": "=You are provided with some client-company conversation and should decide who has to be informed about the feedback. Always only inform one person. Those are your options: \n- It's about a product, send an email to {{ $('Define routing emails here').item.json['Product Email'] }}\n- It's about an invoicing problem, send an email to {{ $('Define routing emails here').item.json['Administrative Email'] }}\n- It's  related to a problem with the product, send an email to {{ $('Define routing emails here').item.json['Support Email'] }}\n- It's commercial related, send an email to {{ $('Define routing emails here').item.json['Commercial Email'] }}\n\nAdd the email of the person (\"{{ $('Enter Client Transcript').item.json['client email'] }}\") at the beginning of the text preceded by \"FROM CLIENT: \"\nUse the Mailjet tool to inform each of the most related department. Provide mailjet with a subject, an email, and the email body formated as html which is the client conversation itself."
        },
        "promptType": "define"
      },
      "notesInFlow": true,
      "typeVersion": 1.8
    },
    {
      "id": "0485667e-befa-4b69-998f-26e1b8a9f67f",
      "name": "Resumen",
      "type": "@n8n/n8n-nodes-langchain.chainSummarization",
      "notes": "The transcript is summarized",
      "position": [
        -360,
        200
      ],
      "parameters": {
        "options": {
          "summarizationMethodAndPrompts": {
            "values": {
              "prompt": "=Summarize the following Converstaion in 2-3 sentences:\n\n\" {{ $json['client conversation'] }}\"\n\nJust output the summarized conversation and nothing else. Use the same language as the input",
              "summarizationMethod": "stuff"
            }
          }
        }
      },
      "notesInFlow": true,
      "typeVersion": 2,
      "alwaysOutputData": false
    },
    {
      "id": "bb2826b5-18ec-4df7-990d-7fe99df759c8",
      "name": "Ingresar transcripción del cliente",
      "type": "n8n-nodes-base.formTrigger",
      "notes": "The transcript can come from fireflies or Team etc.",
      "position": [
        -800,
        200
      ],
      "webhookId": "4ba66bc9-8200-4b29-9d81-aaaca2ca8e0a",
      "parameters": {
        "options": {
          "appendAttribution": false
        },
        "formTitle": "Automate Client issue",
        "formFields": {
          "values": [
            {
              "fieldType": "email",
              "fieldLabel": "client email",
              "requiredField": true
            },
            {
              "fieldType": "textarea",
              "fieldLabel": "client conversation",
              "requiredField": true
            }
          ]
        }
      },
      "notesInFlow": true,
      "typeVersion": 2.2
    },
    {
      "id": "4ec42125-16dd-4c05-8816-3f3d986335ac",
      "name": "Formulario",
      "type": "n8n-nodes-base.form",
      "position": [
        360,
        420
      ],
      "webhookId": "938c1d15-f510-4b66-abac-dca5ff89461d",
      "parameters": {
        "options": {},
        "operation": "completion",
        "completionTitle": "Ouput",
        "completionMessage": "={{ $json.output }}"
      },
      "typeVersion": 1
    },
    {
      "id": "5bdd3903-06f3-4c21-bc57-7127cfc6e433",
      "name": "OpenAI Chat Model",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        -272,
        420
      ],
      "parameters": {
        "model": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-4o-mini"
        },
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "id": "1IOLtYX7aTspCAN8",
          "name": "OpenAI Pollup"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "1abb54f8-0f65-4280-8b35-4dc7c3b1bb07",
      "name": "Definir correos de enrutamiento aquí",
      "type": "n8n-nodes-base.set",
      "position": [
        -580,
        200
      ],
      "parameters": {
        "options": {},
        "assignments": {
          "assignments": [
            {
              "id": "099d5326-3452-47b8-9dc0-acc0e6fd951e",
              "name": "Support Email",
              "type": "string",
              "value": "support@pollup.net"
            },
            {
              "id": "4ed84290-dbf7-47f7-8693-4f95e0c2fd7e",
              "name": "Administrative Email",
              "type": "string",
              "value": "admin@pollup.net"
            },
            {
              "id": "c39edf1f-b8e0-48ca-929c-294bbac52837",
              "name": "Product Email",
              "type": "string",
              "value": "product@pollup.net"
            },
            {
              "id": "614d4a5c-c9f2-4d82-bfcb-cfdcc8a4b07d",
              "name": "Commercial Email",
              "type": "string",
              "value": "commercial@pollup.net"
            }
          ]
        }
      },
      "typeVersion": 3.4
    },
    {
      "id": "c2d345e2-ce32-4337-91d5-ae8bf54e3d25",
      "name": "Gmail",
      "type": "n8n-nodes-base.gmailTool",
      "position": [
        180,
        640
      ],
      "webhookId": "ea898d49-e017-441c-bfe0-7a966435a570",
      "parameters": {
        "sendTo": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('To', ``, 'string') }}",
        "message": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('Message', ``, 'string') }}",
        "options": {
          "appendAttribution": false
        },
        "subject": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('Subject', ``, 'string') }}"
      },
      "credentials": {
        "gmailOAuth2": {
          "id": "DLjspol9TLgpGaXa",
          "name": "Gmail account 2"
        }
      },
      "typeVersion": 2.1
    },
    {
      "id": "11210b0c-c33d-4c40-b20c-a8d3a1761863",
      "name": "Nota adhesiva2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -660,
        100
      ],
      "parameters": {
        "color": 4,
        "width": 260,
        "height": 260,
        "content": "## Set the emails HERE\nFor each responsible in your company."
      },
      "typeVersion": 1
    },
    {
      "id": "0d2e217d-5c3a-4fdb-a60e-091a50de553b",
      "name": "Nota adhesiva7",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -860,
        -120
      ],
      "parameters": {
        "width": 460,
        "height": 200,
        "content": "## Contact me\n- If you need any modification to this workflow\n- if you need some help with this workflow\n- Or if you need any workflow in n8n, Make, or Langchain / Langgraph\n\nWrite to me: [thomas@pollup.net](mailto:thomas@pollup.net)"
      },
      "typeVersion": 1
    },
    {
      "id": "e7e40c88-374b-49d4-8c66-b8543a9376ea",
      "name": "Nota adhesiva3",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -860,
        100
      ],
      "parameters": {
        "color": 4,
        "width": 180,
        "height": 260,
        "content": "## Starting form\n"
      },
      "typeVersion": 1
    }
  ],
  "connections": {
    "c2d345e2-ce32-4337-91d5-ae8bf54e3d25": {
      "ai_tool": [
        [
          {
            "node": "96142f55-cbb4-47e9-a44e-b4f783eeeeb5",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "e4849449-3464-4deb-a9be-07b3d0bb2d56": {
      "main": [
        [
          {
            "node": "d681d557-cb02-4fb1-9871-bfae504992ca",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "96142f55-cbb4-47e9-a44e-b4f783eeeeb5": {
      "main": [
        [
          {
            "node": "4ec42125-16dd-4c05-8816-3f3d986335ac",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "0485667e-befa-4b69-998f-26e1b8a9f67f": {
      "main": [
        [
          {
            "node": "96142f55-cbb4-47e9-a44e-b4f783eeeeb5",
            "type": "main",
            "index": 0
          },
          {
            "node": "e4849449-3464-4deb-a9be-07b3d0bb2d56",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "5bdd3903-06f3-4c21-bc57-7127cfc6e433": {
      "ai_languageModel": [
        [
          {
            "node": "0485667e-befa-4b69-998f-26e1b8a9f67f",
            "type": "ai_languageModel",
            "index": 0
          },
          {
            "node": "96142f55-cbb4-47e9-a44e-b4f783eeeeb5",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "bb2826b5-18ec-4df7-990d-7fe99df759c8": {
      "main": [
        [
          {
            "node": "1abb54f8-0f65-4280-8b35-4dc7c3b1bb07",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "1abb54f8-0f65-4280-8b35-4dc7c3b1bb07": {
      "main": [
        [
          {
            "node": "0485667e-befa-4b69-998f-26e1b8a9f67f",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}
Preguntas frecuentes

¿Cómo usar este flujo de trabajo?

Copie el código de configuración JSON de arriba, cree un nuevo flujo de trabajo en su instancia de n8n y seleccione "Importar desde JSON", pegue la configuración y luego modifique la configuración de credenciales según sea necesario.

¿En qué escenarios es adecuado este flujo de trabajo?

Intermedio - Ventas, Soporte, Inteligencia Artificial, Marketing

¿Es de pago?

Este flujo de trabajo es completamente gratuito, puede importarlo y usarlo directamente. Sin embargo, tenga en cuenta que los servicios de terceros utilizados en el flujo de trabajo (como la API de OpenAI) pueden requerir un pago por su cuenta.

Información del flujo de trabajo
Nivel de dificultad
Intermedio
Número de nodos14
Categoría4
Tipos de nodos9
Descripción de la dificultad

Adecuado para usuarios con experiencia intermedia, flujos de trabajo de complejidad media con 6-15 nodos

Autor
PollupAI

PollupAI

@zeerobug

We create bespoke AI solutions, automations and agents that help your business as it scales.

Enlaces externos
Ver en n8n.io

Compartir este flujo de trabajo

Categorías

Categorías: 34