Telegram AI Chatbot with OpenAI GPT

Overview

This workflow turns your Telegram bot into a smart AI assistant powered by OpenAI's GPT models. Every time someone sends a message to your bot, the workflow forwards it to GPT, generates a context-aware reply, and sends it back — all in a few seconds. It's a cost-effective alternative to paid chatbot platforms, giving you full control over the personality and rules via a system prompt.

How It Works

The workflow is triggered by an incoming Telegram message, processes it through an AI model, and replies to the same chat. Here are the nodes and their roles:

• Telegram Message In (Telegram Bot Token auth) — Watches for new messages in your bot's chat. Configured to listen for message updates only. No additional parameters.
• AI Reply (OpenAI API Key auth) — Sends the user's message to OpenAI's GPT model (here gpt-5.6-luna as a placeholder – you can choose any available model). The request includes a system prompt that defines the bot's behavior (e.g., "You are a helpful, concise assistant...") and the user message from the Telegram trigger. This node has retry on fail enabled (3 retries, 5 seconds apart) to handle transient errors.
• Send Reply (Telegram Bot Token auth) — Takes the AI's response (from $json.message.content) and sends it back to the original chat, using the chat_id from the trigger. No retry is configured to avoid duplicate messages.

Setup Instructions

1. Create a Telegram Bot: Open Telegram, search for @BotFather, and send /newbot. Follow the prompts to get a bot token (e.g., 123456:ABC-DEF1234ghIkl-zyx57W2v1u123ew11).
2. Get an OpenAI API Key: Sign up at platform.openai.com, create an API key, and ensure it has access to the GPT model you want to use.
3. Configure Credentials in n8n:
   • For the Telegram nodes (Trigger and Send), create a new credential of type "Telegram API" and paste your bot token.
   • For the AI Reply node, create a credential of type "OpenAI" and paste your API key.
4. Edit the System Prompt: Open the AI Reply node and modify the system message to change the bot's personality, tone, or knowledge constraints. For example, you can make it a support agent, a tutor, or a sarcastic friend.
5. Activate the Workflow: Once saved, toggle the workflow to "Active". Send a message to your bot on Telegram to test it.

Use Cases & Variations

• Customer Support: Replace the system prompt with your FAQ and company policies to create a 24/7 support bot.
• Personal Assistant: Add a directive to remember context (requires additional memory nodes like Window Buffer Memory) or integrate with calendars/tasks.
• Multi‑language Translator: Change the system prompt to "Translate the user's message to Spanish" and use the AI reply as a translation service.
• Content Generator: Have the bot generate blog posts, jokes, or summaries based on user requests.
• Error Handling: The workflow includes retries on the AI node only. If you want to be notified of failures, add an Error Trigger workflow that sends alerts to Slack or email.

{
  "name": "Telegram AI Chatbot",
  "nodes": [
    {
      "parameters": {
        "content": "## Telegram AI Chatbot Powered by GPT\n\nYour own private AI assistant inside Telegram - or a customer-facing FAQ bot - without paying for a chatbot platform.\n\n**Setup time:** 15 minutes  ·  **Level:** Intermediate\n\n**You'll need accounts/credentials for:** Telegram, OpenAI\n\n**Setup steps:**\n1. Create a bot with @BotFather in Telegram (send /newbot, copy the token).\n2. Add your OpenAI API credential to the AI node - or swap in the Anthropic or Google node.\n3. Edit the system prompt in the AI node to define your bot's personality and rules.\n4. Activate the workflow and message your bot on Telegram.\n\nFree templates and updates: navkhan103.github.io",
        "height": 530,
        "width": 400,
        "color": 4
      },
      "id": "sticky-setup",
      "name": "Setup — read me first",
      "type": "n8n-nodes-base.stickyNote",
      "typeVersion": 1,
      "position": [
        -440,
        -40
      ]
    },
    {
      "parameters": {
        "content": "### How it runs\n\nStarts from **Telegram Message In**.\n\n1. A Telegram Trigger fires whenever someone messages your bot.\n2. An AI node sends the message to GPT with a system prompt you control (support agent, tutor, sarcastic friend - your call).\n3. A Telegram node sends the AI's answer back to the same chat.\n4. Replies land in a couple of seconds and each exchange costs a fraction of a cent.",
        "height": 348,
        "width": 400,
        "color": 7
      },
      "id": "sticky-how",
      "name": "How it runs",
      "type": "n8n-nodes-base.stickyNote",
      "typeVersion": 1,
      "position": [
        -440,
        530
      ]
    },
    {
      "parameters": {
        "content": "### If something breaks\n\nThe read and AI nodes here **retry 3× automatically** (5s apart), which absorbs rate limits and brief timeouts.\n\nNodes that **send or write deliberately do not retry** — a send that reached the far end but lost its response would otherwise fire twice, so you'd get duplicate messages or duplicate rows.\n\nTo be told when one of those fails, build a workflow starting with an **Error Trigger** node that posts to Slack or email, then set it under **three-dot menu > Settings > Error Workflow**. Do it once and point every workflow at it.",
        "height": 400,
        "width": 400,
        "color": 3
      },
      "id": "sticky-fail",
      "name": "If something breaks",
      "type": "n8n-nodes-base.stickyNote",
      "typeVersion": 1,
      "position": [
        -440,
        918
      ]
// ... truncated (copy to see full JSON)