AI Research Helper with Linear, Scrapeless, and Claude

This workflow creates an AI-powered research assistant that dynamically responds to issues or comments in Linear, automating information gathering and analysis from various online sources. The process starts with a Linear trigger detecting specific issue types based on titles. It then directs the flow through a switch node to categorize tasks like search, trends, scrape, or crawl. For each category, dedicated nodes fetch data from Google Search, Google Trends, and Scrapeless services, removing unnecessary parts of the titles with custom code nodes. The gathered data is summarized by an AI model (Claude) and an analysis node to generate concise insights, actionable recommendations, and structured summaries. Finally, the AI-generated insights are posted back as comments or updates on the original Linear issue, providing a seamless, automated research workflow suitable for content creation, competitive analysis, or data-driven decision-making.