AutomationFlowsAI & RAG › AI Customer Support Agent via WhatsApp & Telegram

AI Customer Support Agent via WhatsApp & Telegram

Original n8n title: 🤖 AI Customer Support Agent - Never Sleep, Never Miss a Customer Again!

ByAmanda Benks @amanda on n8n.io

This workflow contains community nodes that are only compatible with the self-hosted version of n8n.

Webhook trigger★★★★☆ complexityAI-powered19 nodesEmail Read ImapNotionOpenAIHTTP RequestEmail Send
AI & RAG Trigger: Webhook Nodes: 19 Complexity: ★★★★☆ AI nodes: yes Added:

This workflow corresponds to n8n.io template #5310 — we link there as the canonical source.

This workflow follows the Emailreadimap → Emailsend 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": "AI Customer Support Agent Multi-Channel",
  "tags": [
    {
      "id": "ai-agent",
      "name": "AI Agent",
      "createdAt": "2025-01-01T00:00:00.000Z",
      "updatedAt": "2025-01-01T00:00:00.000Z"
    },
    {
      "id": "customer-support",
      "name": "Customer Support",
      "createdAt": "2025-01-01T00:00:00.000Z",
      "updatedAt": "2025-01-01T00:00:00.000Z"
    },
    {
      "id": "automation",
      "name": "Automation",
      "createdAt": "2025-01-01T00:00:00.000Z",
      "updatedAt": "2025-01-01T00:00:00.000Z"
    }
  ],
  "nodes": [
    {
      "id": "sticky_note_intro",
      "name": "Sticky Note",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -200,
        200
      ],
      "parameters": {
        "content": ""
      },
      "typeVersion": 1
    },
    {
      "id": "whatsapp_webhook",
      "name": "WhatsApp Webhook",
      "type": "n8n-nodes-base.webhook",
      "position": [
        200,
        300
      ],
      "parameters": {},
      "typeVersion": 2
    },
    {
      "id": "telegram_webhook",
      "name": "Telegram Webhook",
      "type": "n8n-nodes-base.webhook",
      "position": [
        200,
        450
      ],
      "parameters": {},
      "typeVersion": 2
    },
    {
      "id": "email_trigger",
      "name": "Email Trigger",
      "type": "n8n-nodes-base.emailReadImap",
      "position": [
        200,
        600
      ],
      "parameters": {},
      "typeVersion": 2
    },
    {
      "id": "normalize_data",
      "name": "Normalize Message Data",
      "type": "n8n-nodes-base.set",
      "position": [
        500,
        450
      ],
      "parameters": {},
      "typeVersion": 3.4
    },
    {
      "id": "get_conversation_history",
      "name": "Get Conversation History",
      "type": "n8n-nodes-base.notion",
      "position": [
        800,
        450
      ],
      "parameters": {},
      "typeVersion": 2
    },
    {
      "id": "sticky_memory",
      "name": "Sticky Note1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        780,
        200
      ],
      "parameters": {
        "content": ""
      },
      "typeVersion": 1
    },
    {
      "id": "openai_agent",
      "name": "OpenAI Support Agent",
      "type": "n8n-nodes-base.openAi",
      "position": [
        1100,
        450
      ],
      "parameters": {},
      "typeVersion": 1.3
    },
    {
      "id": "sticky_ai",
      "name": "Sticky Note2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1080,
        80
      ],
      "parameters": {
        "content": ""
      },
      "typeVersion": 1
    },
    {
      "id": "check_escalation",
      "name": "Check if Escalation Needed",
      "type": "n8n-nodes-base.if",
      "position": [
        1400,
        450
      ],
      "parameters": {},
      "typeVersion": 2
    },
    {
      "id": "format_response",
      "name": "Format AI Response",
      "type": "n8n-nodes-base.set",
      "position": [
        1700,
        350
      ],
      "parameters": {},
      "typeVersion": 3.4
    },
    {
      "id": "send_whatsapp_response",
      "name": "Send WhatsApp Response",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        2000,
        200
      ],
      "parameters": {},
      "typeVersion": 4.2
    },
    {
      "id": "send_telegram_response",
      "name": "Send Telegram Response",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        2000,
        350
      ],
      "parameters": {},
      "typeVersion": 4.2
    },
    {
      "id": "send_email_response",
      "name": "Send Email Response",
      "type": "n8n-nodes-base.emailSend",
      "position": [
        2000,
        500
      ],
      "parameters": {},
      "typeVersion": 2.1
    },
    {
      "id": "save_conversation",
      "name": "Save Conversation",
      "type": "n8n-nodes-base.notion",
      "position": [
        2300,
        450
      ],
      "parameters": {},
      "typeVersion": 2
    },
    {
      "id": "notify_human_agents",
      "name": "Notify Human Agents",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        1700,
        600
      ],
      "parameters": {},
      "typeVersion": 4.2
    },
    {
      "id": "sticky_escalation",
      "name": "Sticky Note3",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1620,
        720
      ],
      "parameters": {
        "content": ""
      },
      "typeVersion": 1
    },
    {
      "id": "sticky_analytics",
      "name": "Sticky Note4",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        2280,
        200
      ],
      "parameters": {
        "content": ""
      },
      "typeVersion": 1
    },
    {
      "id": "webhook_response",
      "name": "Webhook Response",
      "type": "n8n-nodes-base.respondToWebhook",
      "position": [
        2600,
        450
      ],
      "parameters": {},
      "typeVersion": 1.1
    }
  ],
  "settings": {
    "executionOrder": "v1"
  },
  "updatedAt": "2025-01-01T00:00:00.000Z",
  "versionId": "1",
  "staticData": null,
  "connections": {
    "openai_agent": {
      "main": [
        [
          {
            "node": "check_escalation",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "email_trigger": {
      "main": [
        [
          {
            "node": "normalize_data",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "normalize_data": {
      "main": [
        [
          {
            "node": "get_conversation_history",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "format_response": {
      "main": [
        [
          {
            "node": "send_whatsapp_response",
            "type": "main",
            "index": 0
          },
          {
            "node": "send_telegram_response",
            "type": "main",
            "index": 0
          },
          {
            "node": "send_email_response",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "check_escalation": {
      "main": [
        [
          {
            "node": "format_response",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "format_response",
            "type": "main",
            "index": 0
          },
          {
            "node": "notify_human_agents",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "telegram_webhook": {
      "main": [
        [
          {
            "node": "normalize_data",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "whatsapp_webhook": {
      "main": [
        [
          {
            "node": "normalize_data",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "save_conversation": {
      "main": [
        [
          {
            "node": "webhook_response",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "send_email_response": {
      "main": [
        [
          {
            "node": "save_conversation",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "send_telegram_response": {
      "main": [
        [
          {
            "node": "save_conversation",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "send_whatsapp_response": {
      "main": [
        [
          {
            "node": "save_conversation",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "get_conversation_history": {
      "main": [
        [
          {
            "node": "openai_agent",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  },
  "triggerCount": 3
}
Pro

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

About this workflow

This workflow contains community nodes that are only compatible with the self-hosted version of n8n.

Source: https://n8n.io/workflows/5310/ — 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

This n8n workflow orchestrates a powerful suite of AI Agents and automations to manage and optimize various aspects of an e-commerce operation, particularly for platforms like Shopify. It leverages La

Google Sheets, HTTP Request, Slack +10
AI & RAG

Remi 1.1. Uses lmChatOpenAi, memoryPostgresChat, openAi, postgres. Webhook trigger; 89 nodes.

OpenAI Chat, Memory Postgres Chat, OpenAI +7
AI & RAG

This workflow turns your WhatsApp Business number into a 24/7 AI-powered customer assistant — without any third-party chatbot platform. It receives incoming WhatsApp messages via Evolution API, unders

OpenAI, Information Extractor, Anthropic Chat +7
AI & RAG

This workflow acts as an AI-powered research assistant that takes a topic from the user, performs multi-step intelligent research, and stores the final report in Notion. It uses advanced search, conte

Memory Buffer Window, Output Parser Structured, Agent +6
AI & RAG

fireflies. Uses openAi, httpRequest, emailSend, chainLlm. Webhook trigger; 25 nodes.

OpenAI, HTTP Request, Email Send +3