This project presents a web-based, AI-assisted visual programming platform that lowers the barrier to entry for robotics development with ROS 2. Using a Blockly-to-ROS transpiler, the system turns intuitive drag-and-drop blocks into executable robot logic, abstracting away the steep learning curve of the Robot Operating System. The platform also integrates an autonomous AI coding assistant: rather than relying on error-prone Blockly XML, it uses a custom JSON Domain Specific Language. The system’s viability was demonstrated through a multi-robot co-simulation in which live sensor data from a physical ESP32 (via micro-ROS) drove a simulated UR5 arm in real time—proving the architecture is robust, modular, and ready for educational deployment.