The Department of Energy’s Pacific Northwest National Laboratory has partnered with Amazon Web Services to explore and validate advanced artificial intelligence tools to help operators of the nation’s electric grid respond to severe weather, rising electricity demand and cyber or physical threats. PNNL grid experts will develop and evaluate AI systems with AWS and test scenarios in PNNL’s Electricity Infrastructure Operating Center using a secure, operations-grade hybrid-cloud Amazon environment. The work addresses challenges for utilities, grid planners, technology developers and government stakeholders, including improving situational awareness, reducing operator burden, strengthening grid resilience and helping the grid adapt to faster and more variable supply and demand. The work supports PNNL’s Enhanced Visibility & Event Response capability, launched earlier this spring to develop real-time AI-driven analytics, simulation environments and sensing tools. In May 2025, the Lab published a report detailing opportunities for grid operators to incorporate AI, specifically large language models. However, LLMs can produce errors known as “hallucinations” because they are trained to predict letters or words based on probability and do not actually “know” meaning. Researchers have increasingly looked into neuro-symbolic AI, which combines pattern recognition to combat that challenge.