This study explores the impact of Artificial Intelligence (AI) innovation, economic growth, energy consumption, Foreign Direct Investment (FDI), and urbanization on carbon emissions in the United States over the period 1990–2022. Drawing on the STIRPAT framework, the analysis employs the Autoregressive Distributed Lag (ARDL) model to investigate both short-run and long-run relationships among the variables. Unit root tests confirm a mixed order of integration, justifying the application of the ARDL bounds testing approach. The empirical findings reveal a dual pattern: AI innovation contributes to reducing carbon emissions by improving technological efficiency and promoting cleaner production processes, while economic growth, energy consumption, FDI inflows, and urbanization significantly increase environmental degradation. The results further indicate the presence of a stable long-run equilibrium relationship among the variables. In the short run, fluctuations in economic and structural factors continue to exert pressure on environmental quality. The study highlights that technological progress alone cannot ensure sustainability without effective environmental governance and energy transition strategies. Based on these findings, the study recommends promoting environmentally oriented AI development, accelerating the transition toward clean energy sources, guiding FDI toward green sectors, and implementing sustainable urban planning policies to mitigate carbon emissions and support long-term environmental sustainability in the United States.