Skip to main content

Smart Amazon shopping assistant with Gemini AI and Telegram

Workflow preview

Workflow preview
100%
Smart Amazon shopping assistant with Gemini AI and Telegram preview
Open on n8n.io

Important notice

This workflow is provided as-is. Please review and test before using in production.

1. Workflow Overview

Smart Telegram Shopping Assistant with AI Product Recommendations Workflow Overview Target User Role : E commerce Business Owners, Affiliate Marketers, Customer Support Teams Problem Solved : Bu...

Best for

  • Lead Nurturing automation workflows
  • AI Chatbot automation workflows
  • advanced n8n builders looking for reusable templates

Tools used

@n8n/n8n-nodes-langchain.lmchatgooglegemini, @n8n/n8n-nodes-langchain.outputparserstructured, n8n-nodes-base.telegramtrigger, n8n-nodes-base.code, @n8n/n8n-nodes-langchain.agent, n8n-nodes-base.switch, n8n-nodes-base.telegram, n8n-nodes-base.httprequest

Source and attribution

This workflow is cataloged by N8N Workflows and links back to its original n8n.io source page by Roshan Ramani.

Original n8n.io source

1.1 Workflow description

Title
Smart Amazon shopping assistant with Gemini AI and Telegram
Workflow name
Smart Amazon shopping assistant with Gemini AI and Telegram

🛒 Smart Telegram Shopping Assistant with AI Product Recommendations

Workflow Overview

Target User Role: E-commerce Business Owners, Affiliate Marketers, Customer Support Teams

Problem Solved: Businesses need an automated way to help customers find products on Telegram without manual intervention, while providing intelligent recommendations that increase conversion rates.

Opportunity Created: Transform any Telegram channel into a smart shopping assistant that can handle both product queries and customer conversations automatically.


What This Workflow Does

This workflow creates an intelligent Telegram bot that:

  • 🤖 Automatically detects whether users are asking about products or just chatting
  • 🛒 Scrapes Amazon in real-time to find the best matching products
  • 🎯 Uses AI to analyze and rank products based on price, ratings, and user needs
  • 📱 Delivers perfectly formatted recommendations optimized for Telegram
  • 💬 Handles casual conversations professionally when users aren't shopping

Real-World Use Cases

  • E-commerce Support: Reduce customer service workload by 70%
  • Affiliate Marketing: Automatically recommend products with tracking links
  • Telegram Communities: Add shopping capabilities to existing channels
  • Product Discovery: Help customers find products they didn't know existed

Key Features & Benefits

🧠 Intelligent Intent Detection

  • Uses Google Gemini AI to understand user messages
  • Automatically routes to product search or conversation mode
  • Handles multiple languages and casual typing styles

🛒 Real-Time Product Data

  • Integrates with Apify's Amazon scraper for live data
  • Fetches prices, ratings, reviews, and product details
  • Processes up to 10 products per search instantly

🎯 AI-Powered Recommendations

  • Analyzes multiple products simultaneously
  • Ranks by relevance, value, and user satisfaction
  • Provides top 5 personalized recommendations with reasoning

📱 Telegram-Optimized Output

  • Perfect formatting with emojis and markdown
  • Respects character limits for mobile viewing
  • Includes direct purchase links for easy buying

Setup Requirements

Required Credentials

  1. Telegram Bot Token - Free from @BotFather
  2. Google Gemini API Key - Free tier available at AI Studio
  3. Apify API Token - Free tier includes 100 requests/month

Required n8n Nodes

  • @n8n/n8n-nodes-langchain (for AI functionality)
  • Built-in Telegram, HTTP Request, and Code nodes

Quick Setup Guide

Step 1: Telegram Bot Creation

  1. Message @BotFather on Telegram
  2. Create new bot with /newbot command
  3. Copy the bot token to your credentials

Step 2: AI Configuration

  1. Sign up for Google AI Studio
  2. Generate API key for Gemini
  3. Add credentials to all three AI model nodes

Step 3: Product Scraping Setup

  1. Register for free Apify account
  2. Get API token from dashboard
  3. Add token to "Amazon Product Scraper" node

Step 4: Activation

  1. Import workflow JSON
  2. Add your credentials
  3. Activate the Telegram Trigger
  4. Test with a product query!

Workflow Architecture

📱 Message Entry Point

Telegram Trigger receives all messages

🧹 Query Preprocessing

Cleans and normalizes user input for better search results

🤖 AI Intent Classification

Determines if message is product-related or conversational

🔀 Smart Routing

Directs to appropriate workflow path based on intent

💬 Conversation Path

Handles greetings, questions, and general support

🛒 Product Search Path

Scrapes Amazon → Processes data → AI analysis → Recommendations

📤 Optimized Delivery

Formats and sends responses back to Telegram


Customization Opportunities

Easy Modifications

  • Multiple Marketplaces: Add eBay, Flipkart, or local stores
  • Product Categories: Specialize for electronics, fashion, etc.
  • Language Support: Translate for different markets
  • Branding: Customize responses with your brand voice

Advanced Extensions

  • Price Monitoring: Set up alerts for price drops
  • User Preferences: Remember customer preferences
  • Analytics Dashboard: Track popular products and queries
  • Affiliate Integration: Add commission tracking links

Success Metrics & ROI

Performance Benchmarks

  • Response Time: 3-5 seconds for product queries
  • Accuracy: 90%+ relevant product matches
  • User Satisfaction: 85%+ positive feedback in testing

Business Impact

  • Reduced Support Costs: Automate 70% of product inquiries
  • Increased Conversions: Personalized recommendations boost sales
  • 24/7 Availability: Never miss a customer inquiry
  • Scalability: Handle unlimited concurrent users

Workflow Complexity

Intermediate Level - Requires API setup but includes detailed instructions. Perfect for users with basic n8n experience who want to create something powerful.

1.2 Logical Blocks

This catalog entry is organized from the workflow JSON. The node-level section below shows the executable blocks available for review before importing the template.

2. Block-by-Block Analysis

Block 1 - Google Gemini Chat Model1

Type / Role
@n8n/n8n-nodes-langchain.lmChatGoogleGemini - lmChatGoogleGemini
Config choices
Version 1

Block 2 - Google Gemini Chat Model2

Type / Role
@n8n/n8n-nodes-langchain.lmChatGoogleGemini - lmChatGoogleGemini
Config choices
Version 1

Block 3 - Structured Output Parser

Type / Role
@n8n/n8n-nodes-langchain.outputParserStructured - outputParserStructured
Config choices
Version 1.3

Block 4 - Google Gemini Chat Model3

Type / Role
@n8n/n8n-nodes-langchain.lmChatGoogleGemini - lmChatGoogleGemini
Config choices
Version 1

Block 5 - Telegram Message Receiver

Type / Role
n8n-nodes-base.telegramTrigger - telegramTrigger
Config choices
Version 1.2

Block 6 - Product Query Cleaner

Type / Role
n8n-nodes-base.code - code
Config choices
Version 2

Block 7 - Message Intent Classifier

Type / Role
@n8n/n8n-nodes-langchain.agent - agent
Config choices
Version 2

Block 8 - Product vs Chat Router

Type / Role
n8n-nodes-base.switch - switch
Config choices
Version 3.2

Block 9 - Chat Response Generator

Type / Role
@n8n/n8n-nodes-langchain.agent - agent
Config choices
Version 2

Block 10 - Send Chat Response

Type / Role
n8n-nodes-base.telegram - telegram
Config choices
Version 1.2

Block 11 - Amazon Product Scraper

Type / Role
n8n-nodes-base.httpRequest - httpRequest
Config choices
Version 4.2

Block 12 - Product Data Processor

Type / Role
n8n-nodes-base.code - code
Config choices
Version 2

Block 13 - Product List Combiner

Type / Role
n8n-nodes-base.aggregate - aggregate
Config choices
Version 1

Block 14 - Product Recommendation Engine

Type / Role
@n8n/n8n-nodes-langchain.agent - agent
Config choices
Version 2.1

Block 15 - Send Product Recommendations

Type / Role
n8n-nodes-base.telegram - telegram
Config choices
Version 1.2

Block 16 - Sticky Note

Type / Role
n8n-nodes-base.stickyNote - stickyNote
Config choices
Version 1

3. Summary Table

Workflow Smart Amazon shopping assistant with Gemini AI and Telegram
Complexity advanced
Nodes 16
Categories Lead Nurturing, AI Chatbot
Author Roshan Ramani
Published 24 Jul 2025

4. Reproducing the Workflow from Scratch

  1. 1. Download the workflow JSON

    Use the JSON export at /data/workflows/6384/6384.json as the source template for this automation.

  2. 2. Import the template into n8n

    Open n8n, import the downloaded JSON, and review each node before activating the workflow.

  3. 3. Configure credentials and variables

    Replace placeholder credentials, API keys, webhook URLs, account IDs, and environment-specific values with your own settings.

  4. 4. Test with sample data

    Run the workflow manually or in a staging workspace, inspect node output, and confirm downstream systems receive the expected data.

  5. 5. Activate and monitor

    Enable the workflow only after testing, then monitor executions, errors, and rate limits during the first production runs.

5. General Notes & Resources

Review imported nodes carefully before activation. This catalog entry is intended to help you inspect the workflow structure, understand required services, and find related templates faster.

Node names, credentials, schedules, webhook paths, and external service limits may need adjustment for your workspace.

Frequently asked questions

What does Smart Amazon shopping assistant with Gemini AI and Telegram do?

Smart Telegram Shopping Assistant with AI Product Recommendations Workflow Overview Target User Role : E commerce Business Owners, Affiliate Marketers, Customer Support Teams Problem Solved : Bu...

What do I need before importing this workflow?

Review the workflow JSON, configure any required credentials in n8n, and test the automation in a safe workspace before using it in production.

Can I customize this workflow?

Yes. Use the block-by-block analysis and the downloadable JSON to inspect each node, then adjust credentials, prompts, schedules, filters, or destinations for your Lead Nurturing, AI Chatbot use case.