AutomationFlowsAI & RAG › Subagente Suporte a Duvidas

Subagente Suporte a Duvidas

SubAgente Suporte a Duvidas. Uses executeWorkflowTrigger, agent, lmChatGoogleGemini, memoryBufferWindow. Event-driven trigger; 4 nodes.

Event trigger★★☆☆☆ complexityAI-powered4 nodesExecute Workflow TriggerAgentGoogle Gemini ChatMemory Buffer Window
AI & RAG Trigger: Event Nodes: 4 Complexity: ★★☆☆☆ AI nodes: yes Added:

This workflow follows the Agent → Execute Workflow Trigger recipe pattern — see all workflows that pair these two integrations.

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 →

Download .json
{
  "name": "SubAgente Suporte a Duvidas",
  "nodes": [
    {
      "parameters": {
        "workflowInputs": {
          "values": [
            {
              "name": "mensagem"
            },
            {
              "name": "ChatID"
            }
          ]
        }
      },
      "type": "n8n-nodes-base.executeWorkflowTrigger",
      "typeVersion": 1.1,
      "position": [
        0,
        0
      ],
      "id": "4450db77-6879-404b-8f27-19e29d5d1aef",
      "name": "When Executed by Another Workflow"
    },
    {
      "parameters": {
        "promptType": "define",
        "text": "={{ $json.mensagem }}",
        "options": {
          "systemMessage": "=# Identidade\nVoc\u00ea \u00e9 o Leo, Analista T\u00e9cnico da Hashtag Capital.\nSeu tom \u00e9: Especialista, did\u00e1tico, seguro e paciente (\ud83d\udcca, \ud83e\udde0).\n\n# Contexto Temporal\nA data e hora exata de hoje \u00e9: {{ $now }}.\nUse esta data como refer\u00eancia para falar sobre fechamento de mercado ou prazos.\n\n# SUA FUN\u00c7\u00c3O\n1. Educador: Tirar d\u00favidas conceituais sobre produtos (CDB, A\u00e7\u00f5es, FIIs, Tesouro). Explique como funcionam.\n\n# Exemplos de Atua\u00e7\u00e3o\n- \"O que \u00e9 Selic?\" -> Explique a taxa b\u00e1sica de juros e impacto na Renda Fixa.\n\n# Limite de Atua\u00e7\u00e3o\nVoc\u00ea explica O QUE \u00c9 o produto, mas N\u00c3O FAZ RECOMENDA\u00c7\u00c3O DE COMPRA (\"Compre PETR4 agora\").\nSe o cliente pedir indica\u00e7\u00e3o personalizada, diga: \"Para uma recomenda\u00e7\u00e3o personalizada para seu perfil, o ideal \u00e9 falar com nosso Assessor.\" (Mas n\u00e3o agende, deixe ele pedir ou sugira procurar o CS).\n\n# REGRA DE TEXTO (IMPORTANTE)\nVoc\u00ea est\u00e1 em um chat simples que quebra se receber c\u00f3digos.\n1. Escreva como se fosse um bloco de notas simples.\n2. NUNCA use negrito, it\u00e1lico, asteriscos ou c\u00f3digos de formata\u00e7\u00e3o.\n\n\n## Regra de sa\u00edda\nSe o assunto for FINANCEIRO (Pagamento, boletos, etc) ou AGENDAMENTO COM ASSESSOR (CS), responda apenas:\n##RESET##"
        }
      },
      "type": "@n8n/n8n-nodes-langchain.agent",
      "typeVersion": 3.1,
      "position": [
        208,
        0
      ],
      "id": "4908caf8-6254-4cb9-8edd-dda801f67cd9",
      "name": "AI Agent"
    },
    {
      "parameters": {
        "modelName": "models/gemini-2.5-flash-lite",
        "options": {}
      },
      "type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
      "typeVersion": 1.1,
      "position": [
        208,
        176
      ],
      "id": "5d992eb1-fbf2-4f60-b5b9-346ebd309bdd",
      "name": "Google Gemini Chat Model",
      "credentials": {
        "googlePalmApi": {
          "name": "<your credential>"
        }
      }
    },
    {
      "parameters": {
        "sessionIdType": "customKey",
        "sessionKey": "={{ $json.ChatID }}",
        "contextWindowLength": 50
      },
      "type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
      "typeVersion": 1.4,
      "position": [
        304,
        336
      ],
      "id": "0fc847d2-4bd4-4f4a-b05c-565fe8488003",
      "name": "Simple Memory"
    }
  ],
  "connections": {
    "When Executed by Another Workflow": {
      "main": [
        [
          {
            "node": "AI Agent",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Google Gemini Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "AI Agent",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Simple Memory": {
      "ai_memory": [
        [
          {
            "node": "AI Agent",
            "type": "ai_memory",
            "index": 0
          }
        ]
      ]
    }
  },
  "active": true,
  "settings": {
    "executionOrder": "v1",
    "binaryMode": "separate"
  },
  "versionId": "3102a0f9-cfc2-45d2-b793-1b74093fe9c4",
  "meta": {
    "templateCredsSetupCompleted": true
  },
  "nodeGroups": [],
  "id": "JrrvrUNJd2awJMDP",
  "tags": [
    {
      "updatedAt": "2026-06-09T23:52:15.221Z",
      "createdAt": "2026-06-09T23:52:15.221Z",
      "id": "B4ukWVnwIRin4fDM",
      "name": "Hashtag"
    }
  ]
}

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.

Pro

For the full experience including quality scoring and batch install features for each workflow upgrade to Pro

About this workflow

SubAgente Suporte a Duvidas. Uses executeWorkflowTrigger, agent, lmChatGoogleGemini, memoryBufferWindow. Event-driven trigger; 4 nodes.

Source: https://github.com/rauldsordi/n8n-financial-multiagent/blob/main/agent-support.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.

AI & RAG

Finance Agent. Uses agent, memoryBufferWindow, executeWorkflowTrigger, dataTableTool. Event-driven trigger; 11 nodes.

Agent, Memory Buffer Window, Execute Workflow Trigger +2
AI & RAG

Homelab IT Agent. Uses dataTableTool, executeWorkflowTrigger, agent, lmChatGoogleGemini. Event-driven trigger; 11 nodes.

Data Table Tool, Execute Workflow Trigger, Agent +3
AI & RAG

Calendar agent. Uses googleCalendarTool, memoryBufferWindow, agent, lmChatGoogleGemini. Event-driven trigger; 10 nodes.

Google Calendar Tool, Memory Buffer Window, Agent +2
AI & RAG

Homelab CLI agent. Uses executeWorkflowTrigger, agent, lmChatGoogleGemini, memoryBufferWindow. Event-driven trigger; 6 nodes.

Execute Workflow Trigger, Agent, Google Gemini Chat +2
AI & RAG

My_gmail_calendar. Uses executeWorkflowTrigger, agent, lmChatGoogleGemini, memoryBufferWindow. Event-driven trigger; 6 nodes.

Execute Workflow Trigger, Agent, Google Gemini Chat +2