Telegram Bot for Budget Queries

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 →

{
  "name": "My workflow 5",
  "nodes": [
    {
      "parameters": {},
      "type": "n8n-nodes-base.manualTrigger",
      "typeVersion": 1,
      "position": [
        0,
        0
      ],
      "id": "91815489-2066-4fb5-a6a9-dd70870b7805",
      "name": "When clicking \u2018Execute workflow\u2019"
    },
    {
      "parameters": {
        "options": {}
      },
      "type": "@n8n/n8n-nodes-langchain.chatTrigger",
      "typeVersion": 1.4,
      "position": [
        208,
        0
      ],
      "id": "184c0026-b634-46a4-87c5-81f2f1c7af9b",
      "name": "When chat message received"
    },
    {
      "parameters": {
        "options": {
          "systemMessage": "You are a Data Insights Interpretation Agent.\n\nIMPORTANT:\nYou will receive a PDF file as input.\n\nThis PDF contains FINAL RESULTS of a data analysis already executed in Jupyter Notebook.\nThe PDF may include:\n- Written textual results (e.g. Top 10 cities, summaries, conclusions)\n- Tables\n- Charts and plots\n\nYour task is to INTERPRET the CONTENT of the PDF only.\n\nRules:\n- Do NOT generate code.\n- Do NOT redo calculations.\n- Do NOT explain how the analysis was performed.\n- Do NOT assume access to raw data.\n- Treat all results in the PDF as correct and final.\n\nWhat you should do:\n1. Read and understand the textual insights in the PDF.\n2. Interpret rankings (e.g. \"Top 10 cities\") and explain their meaning.\n3. Extract key insights from tables and charts conceptually.\n4. Highlight important patterns, dominance, trends, or concentrations.\n5. Translate results into clear conclusions or implications.\n6. If relevant, provide high-level recommendations based on the results.\n\nOutput requirements:\n- Clear structured interpretation\n- Bullet points or short paragraphs\n- Business / analytical language\n- No technical or implementation details\n\nYour role is interpretation and insight generation only.\nAssume the PDF is the single source of truth.\nIf charts are present, interpret their trends conceptually without referring to axes or code.\n"
        }
      },
      "type": "@n8n/n8n-nodes-langchain.agent",
      "typeVersion": 3,
      "position": [
        416,
        0
      ],
      "id": "7e8b13e1-fdce-488c-8976-4bf28ecd1ff8",
      "name": "AI Agent"
    },
    {
      "parameters": {
        "options": {}
      },
      "type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
      "typeVersion": 1,
      "position": [
        288,
        208
      ],
      "id": "be137715-c0d4-4fa5-a001-6222a6642d6a",
      "name": "Google Gemini Chat Model"
    },
    {
      "parameters": {
        "sendTo": "yamamajamea2003@outlook.com",
        "subject": "s",
        "message": "s",
        "options": {}
      },
      "type": "n8n-nodes-base.gmail",
      "typeVersion": 2.2,
      "position": [
        768,
        0
      ],
      "id": "2ff6912f-3519-414c-b315-cc18abb676f3",
      "name": "Send a message",
      "credentials": {
        "gmailOAuth2": {
          "name": "<your credential>"
        }
      }
    }
  ],
  "connections": {
    "When clicking \u2018Execute workflow\u2019": {
      "main": [
        [
          {
            "node": "AI Agent",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "When chat message received": {
      "main": [
        [
          {
            "node": "AI Agent",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Google Gemini Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "AI Agent",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "AI Agent": {
      "main": [
        [
          {
            "node": "Send a message",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  },
  "active": false,
  "settings": {
    "executionOrder": "v1"
  },
  "versionId": "2fcb0eb5-a367-473a-8f40-f4ef481610e6",
  "id": "5IMV7apG0770KjcF",
  "tags": []
}

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.

• googleSheetsOAuth2Api
• telegramApi

How this works

This workflow streamlines customer interactions by automating responses to Telegram messages, enabling businesses to efficiently handle enquiries about products or services while logging details for follow-up. It's ideal for small business owners or customer support teams managing high-volume chats without constant manual intervention, saving hours on repetitive tasks. The key step involves a switch node that routes incoming messages to appropriate replies or data capture, seamlessly integrating with Google Sheets to store chat IDs, categories, and budgets for easy tracking and analysis.

Use this workflow when you need real-time automation for Telegram-based customer service, such as qualifying leads by category and budget before escalating to human agents. Avoid it for non-event-driven scenarios like scheduled reports, or if your team prefers email over messaging apps. Common variations include adding email notifications after sheet updates or expanding the switch logic to handle multiple languages.

About this workflow

My workflow 5. Uses telegramTrigger, telegram, googleSheets. Event-driven trigger; 18 nodes.

Source: https://github.com/FlowLogicLabs/telegram-laptop-sales-bot/blob/main/catalogue/workflow/telegram_laptop_sales_bot.json — original creator credit. Request a take-down →

More Slack & Telegram workflows → · Browse all categories →

Related workflows

Workflows that share integrations, category, or trigger type with this one. All free to copy and import.