Democratizing AI: Expert-Tested VPL-Based Prototype to Foster Participation

This work explores the potential of Visual Programming Languages (VPLs) and no-code platforms to foster participation among users with limited computing experience in the design of ML-based systems. Conducting expert-based testing of the PyFlowML prototype, our preliminary research focuses on developing trustworthy ML-based prototypes that provide Explainable AI (XAI) techniques. Our evaluation employs heuristic methods and direct interactions with experts using the prototype. Utilizing cognitive walkthroughs with a think-aloud protocol, along with quantitative assessments such as task completion time and the System Usability Scale (SUS), our findings highlight the need of streamlining ML processes to enhance broader participation. These insights lay the groundwork for future research aimed at making the design of ML-based systems more accessible and collaborative through VPL-based tools.