Forums
I built an AI agent that turns natural language into editable automation workflows
I've been exploring a question: Why is automation still so difficult for non-developers? Traditional automation tools are powerful, but building a workflow often requires manually finding every button, selector, condition, and exception. I built Runavelo to experiment with a different approach: Instead of manually creating every step, you describe the goal: "Open a website, search for products, collect prices and ratings, and save the results to Excel." AI analyzes the interface and creates a visual workflow: Open Browser Input Search Click Extract Data Loop Pages Export Results The workflow is not a black box. You can still edit every node, add conditions, change parameters, and ask AI to improve it. When something fails, AI analyzes execution logs and helps identify the problem. I'm curious: Do you think AI-generated workflows will replace traditional automation builders? Or will AI simply become another layer on top of existing tools?