Who is this workflow for? This workflow automates the enrichment of company data stored in a Google Sheet by leveraging n8n, OpenAI, and ScrapingBee. It retrieves company details, scrapes relevant website information, processes the data with AI, and updates the spreadsheet with enriched insights..

What does this workflow do?

Main Workflow

  • Webhook Trigger
  • Initiates the workflow through a webhook call.
  • Can be replaced with other triggers such as form submissions or new Google Sheets rows.
  • Get Rows from Google Sheet
  • Retrieves the list of companies from a specified Google Sheet.
  • Required columns: Company, Website.
  • Optional columns for enrichment: Business Area, Offer, Value Proposition, Business Model, ICP, Additional Information.
  • Loop Over Items
  • Iterates through each row in the Google Sheet to process individual companies.
  • Ensures that each company’s website is correctly matched with its respective row.
  • AI Agent Processing
  • Configured with OpenAI’s GPT-4 model to analyze and extract business data from scraped content.
  • Sub-nodes include:
    • OpenAI: Uses the gpt4-o-mini model for data extraction.
    • Call n8n Workflow: Invokes the ScrapingBee workflow to retrieve website data.
    • Structured Output Parser: Formats the AI output and updates the Google Sheet with enriched data.
  • Update Company Row in Google Sheet
  • Inserts the enriched data back into the corresponding row in the Google Sheet, ensuring data consistency and completeness.

Scraper Agent Workflow

  • Tool Called from Agent
  • Triggered by the AI Agent to initiate the scraping process.
  • Sends company name and website URL for data retrieval.
  • Set Company URL
  • Renames and prepares the URL field for data transformation.
  • ScrapingBee: Scrape Company’s Website
  • Utilizes ScrapingBee to extract data from the provided website URL.
  • Configurable scraper settings allow customization of scraping behavior.
  • HTML to Markdown
  • Converts scraped HTML content into Markdown format.
  • Reduces token usage for more efficient processing by OpenAI.

🤖 Why Use This Automation Workflow?

  • Automated Data Enrichment: Streamlines the process of enhancing company information without manual intervention.
  • AI-Powered Insights: Utilizes OpenAI to analyze and extract meaningful business attributes from scraped data.
  • Scalable and Customizable: Easily adapts to different data sources and can be integrated with various tools to fit specific needs.

👨‍💻 Who is This Workflow For?

  • Sales and Marketing Teams: Enhance lead databases with detailed company information for targeted outreach.
  • Data Analysts: Automate the collection and enrichment of company data for comprehensive analysis.
  • Business Development Professionals: Gain deeper insights into potential partners or competitors by enriching existing data sets.

🎯 Use Cases

  1. Lead Generation: Automatically enrich leads in a CRM by pulling additional data from their websites.
  2. Market Research: Compile detailed profiles of companies for competitive analysis and strategic planning.
  3. Customer Profiling: Enhance customer records with in-depth business information to improve service offerings and personalization.

TL;DR

This n8n workflow automates the enrichment of company data in Google Sheets by integrating scraping and AI analysis. It streamlines data collection, enhances information accuracy, and provides actionable business insights, making it an invaluable tool for sales, marketing, and data-driven decision-making.

Help us find the best n8n templates

About

A curated directory of the best n8n templates for workflow automations.