US uses AI to speed up nuclear technology licensing applications

The United States Department of Energy (DOE) has successfully employed artificial intelligence (AI) to expedite the nuclear regulatory licensing process. Using Everstar’s Gordian AI solution, built on Microsoft Azure, the DOE converted a Preliminary Documented Safety Analysis for the National Reactor Innovation Center’s Generic High Temperature Gas Reactor into sections equivalent to a U.S. Nuclear Regulatory Commission (NRC) license application. This AI-driven process produced a comprehensive 208-page document in just one day, a task that traditionally requires four to six weeks by a human team. The AI tool also identified missing or incomplete information necessary for a successful NRC application, enhancing both efficiency and accuracy. Gordian AI is specifically designed for nuclear-grade technical work, integrating physics and engineering tools with semantic ontology mapping to ensure outputs are computed and verified rather than inferred. DOE officials and industry leaders emphasize that this advancement could transform how regulatory submissions are prepared and accelerate the commercial deployment of advanced nuclear reactors while maintaining rigorous safety and compliance standards. The collaboration between DOE