Handling deformable materials presents significant challenges due to their inherent flexibility, tendency to wrinkle, and misalignment during processing. Research into the automation of such materials—particularly textiles and industrial fabrics—has highlighted the im-portance of mechanical optimization, machine vision, sensor integration, and advanced control methods such as deep learning. In collaboration with the air filter manufacturer, this thesis presents the development of a conceptual robotic tool designed to automate key tasks in the assembly of air filter bags. The tool is capable of picking up a filter bag, orienting it vertically with an open mouth, and positioning it for insertion into a stretching machine. The research adopts a structured design thinking methodology, starting with a thorough definition of design requirements, progressing through CAD modeling, prototyping, and culminating in functional testing and iterative optimization. The developed tool was evaluated using a series of experiments on various filter bag samples and demonstrated a success rate of 88%, with identified potential for further improvement. The air filter bag manufacturer has evaluated the conceptual design as promising, especially due to its compact form factor and potential to reduce manual labor. Functionally, the tool has proven well-aligned with its intended application, showing a strong foundation for future industrial implementation