Skip to main content

Compare products and generate visual scorecards in Telegram with BrowserAct and Gemini

Workflow preview

Workflow preview
100%
Compare products and generate visual scorecards in Telegram with BrowserAct and Gemini preview
Open on n8n.io

1. Workflow Overview

Compare products and generate visual scorecards in Telegram using BrowserAct & Nano banana This workflow acts as an expert shopping assistant that analyzes product comparisons from first principles...

Best for

  • Market Research automation workflows
  • AI Chatbot automation workflows
  • advanced n8n builders looking for reusable templates

Tools used

@n8n/n8n-nodes-langchain.outputparserstructured, @n8n/n8n-nodes-langchain.agent, @n8n/n8n-nodes-langchain.lmchatgooglegemini, n8n-nodes-base.splitinbatches, n8n-nodes-base.telegramtrigger, n8n-nodes-base.switch, n8n-nodes-base.telegram, n8n-nodes-base.googlesheets

Source and attribution

This workflow is cataloged by N8N Workflows and links back to its original n8n.io source page by Madame AI Team | Kai.

Original n8n.io source

1.1 Workflow description

Title
Compare products and generate visual scorecards in Telegram with BrowserAct and Gemini
Workflow name
Compare products and generate visual scorecards in Telegram with BrowserAct and Gemini

Compare products and generate visual scorecards in Telegram using BrowserAct & Nano banana

This workflow acts as an expert shopping assistant that analyzes product comparisons from first principles and generates a high-quality visual infographic with the verdict. Instead of reading endless reviews, simply ask the bot (e.g., "iPhone 15 vs S24"), and it will scrape data, analyze it using AI, and render a "Winner Takes All" image card directly in your chat.

Target Audience

Shoppers, tech enthusiasts, product reviewers, and anyone who wants objective, data-driven buying advice without the fluff.

How it works

  1. Understand Intent: The workflow receives a message via Telegram. An AI Classifier determines if you want to chat casually or compare specific products.
  2. Scrape Data: If a comparison is requested, BrowserAct executes a background task to scrape real-time specifications, pricing, and reviews from relevant sites (like Amazon or G2) for each product.
  3. Deep Analysis: An AI Analyst aggregates the data and evaluates it based on Composition, Performance, and Economics to find an objective winner.
  4. Visual Engineering: A second AI Agent generates a detailed "blueprint" prompt for a comparison infographic, highlighting the key differences and the winner.
  5. Render & Deliver: Google Gemini generates a 4K image based on the blueprint, which is then sent to your Telegram chat along with a formatted summary caption.

How to set up

  1. Configure Credentials: Connect your Telegram, Google Sheets, BrowserAct, and Google Gemini accounts in n8n.
  2. Prepare BrowserAct: Ensure the Product Comparison & Visualize Bot template is saved in your BrowserAct account.
  3. Setup Google Sheet: Create a new Google Sheet to serve as a temporary data store.
  4. Connect Sheet: Open the Get row(s) in sheet and Append row in sheet nodes and paste your spreadsheet ID.
  5. Configure Telegram: Ensure your bot is created via BotFather and the API token is added to the Telegram credentials.
  6. Activate: Turn on the workflow.

Requirements

  • BrowserAct account with the Product Comparison & Visualize Bot template.
  • Telegram account (Bot Token).
  • Google Sheets account.
  • Google Gemini account.

How to customize the workflow

  1. Change Image Style: Modify the system prompt in the Generate Image and Description agent to change the aesthetic of the infographic (e.g., "Minimalist," "Cyberpunk," "Corporate").
  2. Adjust Analysis Logic: Update the system prompt in the Analyze the data agent to weigh certain factors more heavily (e.g., prioritize "Price" over "Performance").
  3. Add More Sources: Update the BrowserAct template to scrape specialized niche sites for better data accuracy.

Need Help?


Workflow Guidance and Showcase Video

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 - Structured Output Parser

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

Block 2 - Validate user Input

Type / Role
@n8n/n8n-nodes-langchain.agent - agent
Config choices
Version 3

Block 3 - Google Gemini

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

Block 4 - Loop Over Items

Type / Role
n8n-nodes-base.splitInBatches - splitInBatches
Config choices
Version 3

Block 5 - Structured Output

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

Block 6 - Structured Output1

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

Block 7 - Generate Image and Description

Type / Role
@n8n/n8n-nodes-langchain.agent - agent
Config choices
Version 3

Block 8 - Analyze the data

Type / Role
@n8n/n8n-nodes-langchain.agent - agent
Config choices
Version 3

Block 9 - User Sends Message to Bot

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

Block 10 - Validation Type Switch

Type / Role
n8n-nodes-base.switch - switch
Config choices
Version 3.4

Block 11 - Process Initialization Alert

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

Block 12 - Clear Database

Type / Role
n8n-nodes-base.googleSheets - googleSheets
Config choices
Version 4.7

Block 13 - Split Out Extracted Products

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

Block 14 - Search for each product's data.

Type / Role
n8n-nodes-browseract.browserAct - browserAct
Config choices
Version 1

Block 15 - Save Product Information to Database

Type / Role
n8n-nodes-base.googleSheets - googleSheets
Config choices
Version 4.7

Block 16 - Google Gemini 1

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

Block 17 - Google Gemini 2

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

Block 18 - Google Gemini 3

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

Block 19 - Retrieve Data from Database

Type / Role
n8n-nodes-base.googleSheets - googleSheets
Config choices
Version 4.7

Block 20 - Aggregate Google Sheet Data

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

Block 21 - Generate Comparison Image

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

Block 22 - Send Photo Message to Bot

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

Block 23 - Answer the User

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

Block 24 - Conversational AI

Type / Role
@n8n/n8n-nodes-langchain.agent - agent
Config choices
Version 3

Showing the first 24 of 31 workflow blocks. Download the JSON for the full node graph.

3. Summary Table

Workflow Compare products and generate visual scorecards in Telegram with BrowserAct and Gemini
Complexity advanced
Nodes 31
Categories Market Research, AI Chatbot
Author Madame AI Team | Kai
Published 01 Jan 2026

4. Reproducing the Workflow from Scratch

  1. 1. Download the workflow JSON

    Use the JSON export at /data/workflows/12357/12357.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 Compare products and generate visual scorecards in Telegram with BrowserAct and Gemini do?

Compare products and generate visual scorecards in Telegram using BrowserAct & Nano banana This workflow acts as an expert shopping assistant that analyzes product comparisons from first principles...

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 Market Research, AI Chatbot use case.