n8n + AI: Draft a reply for New Messages Automatically with a Telegram Alert

Every time a customer messages you on WhatsApp, this workflow hands it to Claude, which drafts a ready-to-send reply in your brand voice. You get AI-drafted replies waiting in your inbox without lifting a finger.

difficulty Advancedsetup 45 minresult AI-drafted replies waiting in your inbox
  1. 1

    Trigger when a customer messages you on WhatsApp

    A WhatsApp Trigger starts the workflow the moment a customer messages you on WhatsApp.

  2. 2

    Hand it to the AI agent

    An AI Agent node running Claude drafts a ready-to-send reply in your brand voice. The prompt is pre-written and scoped to this one job so results stay consistent.

  3. 3

    Deliver the reply

    The result is sent to Telegram — with the original for context.

  4. 4

    Add a safety net (optional)

    Insert an IF/human-approval step before anything is published or emailed, so you stay in control until you trust the output.

Frequently asked questions

Does this need n8n Cloud or can I self-host?

Either works. The workflow is a standard n8n export, so you can run it on n8n Cloud or on your own self-hosted instance — you only connect your own app credentials.

How do I import the workflow into n8n?

Download the JSON, then in n8n open a new workflow, choose ⋯ → Import from file, and select it. Every trigger, node and connection appears on the canvas; you just add your credentials and activate it.

How much does the AI part cost to run?

Pennies. Each run sends a small amount of text to the model, so most teams spend a few dollars a month even at hundreds of runs. You set the model and can cap volume in n8n, so costs never surprise you.

About this recipe. Recipes on FlowRecipesHub are written for business owners, not developers, and are tested before publishing — how recipes get made. Some ingredient links are affiliate links that cost you nothing — full disclosure.