Lessons Learned from Multi-Year Operation of a Cloud-Hosted Commercial Robot Driven by Domain-Specific Language Models

The concept of self-driving chemical laboratories builds on top of two technologies: robust artificial intelligence models that translate synthesis designs into executable instructions, potentially incorporating instrument feedback, and robotic workstations capable of executing those procedures seamlessly and without human intervention. Here we present RoboRXN, a cloud-native framework that unifies transformer-based retrosynthesis and chemical action extraction or prediction models with a commer