This n8n workflow automates the process of scraping, analyzing, and summarizing company data from Indeed using Bright Data Web Unlocker, integrating AI-powered language models, and storing results in Airtable. It is designed for HR and recruiting teams or data analysts seeking quick insights into company profiles.

The workflow begins with a manual trigger, allowing users to initiate data collection. It sets a specific Bright Data zone for web unlocking and fetches company pages from Indeed based on links stored in Airtable. If a valid link exists, the workflow performs web requests through Bright Data to extract the company information.

Data retrieved from the web is then processed through various AI nodes. An AI agent using Google’s Gemini model formats and structures the search results, which are then summarized with a specialized summarization chain. The summarized results, along with raw web data, are formatted into markdown and converted to HTML for presentation.

Finally, the workflow sends the formatted HTML content to a webhook, enabling further use or display. Additional notes explain the setup requirements for Airtable and Bright Data. This automation adds significant efficiency for tasks involving web scraping, data analysis, and content generation, useful for business intelligence, market research, or employment insights.

Node Count	11 – 20 Nodes
Nodes Used	@n8n/n8n-nodes-langchain.agent, @n8n/n8n-nodes-langchain.chainLlm, @n8n/n8n-nodes-langchain.chainSummarization, @n8n/n8n-nodes-langchain.lmChatGoogleGemini, @n8n/n8n-nodes-langchain.toolHttpRequest, airtable, httpRequest, if, manualTrigger, markdown, set, splitInBatches, stickyNote, wait