Amazon Web Services (AWS) has announced a program that uses AI agents to help utilities accelerate interconnection studies, with Duke Energy as the collaborating utility.

Through the program, called Agentic Grid Planning on AWS, utilities can use AWS-managed AI agents to carry out portions of interconnection study workflows using the physics-based simulation software, grid models, scripts and engineering standards already used by their teams.

Duke Energy has reduced data preparation tasks from about two weeks of manual work to hours using the AI agents, according to AWS.

The program comes as utilities face increasing volumes and complexity in interconnection studies. According to Lawrence Berkeley National Laboratory, more than 2,000 GW of generation and storage were seeking U.S. transmission interconnection at the end of 2025. Projects entering operation that year had spent a median of more than five years in the interconnection process. In ERCOT, requests to connect large loads reached approximately 410 GW in March 2026.

AWS said the demand for interconnection studies is also outpacing the number of qualified engineers available to perform them.

The AI agents can automate and coordinate study workflows, including data preparation and analysis execution. The simulation software performs the deterministic modeling and analysis, while engineers direct the studies and make the final engineering decisions.

AWS worked with Duke Energy engineers to develop the program. Duke Energy provided transmission planning expertise and feedback during development. Its engineers are using the AI agents to automate and enhance portions of the interconnection process, with the goal of increasing planner capacity and improving efficiency.

The companies also are working to expand the capabilities into large-load planning workflows and establish a foundation for load and generation studies.

"Duke Energy maintains one of the largest utility grids in the United States, and our engineers must complete a higher volume of increasingly complex studies as demand for generation and load grows," said John Pressley, managing director of Digital Strategy and Engineering at Duke Energy. "Our engineers lead the work and make all final engineering decisions, while AI agents provide them with more time for engineering judgment and review."

Interconnection processes are also changing as utilities and grid operators seek to shorten study timelines. FERC Order No. 2023 requires transmission providers to use first-ready, first-served cluster studies and meet study deadlines for generator interconnection. ERCOT, NYISO and SPP also are developing new interconnection processes for large loads.

Agentic Grid Planning on AWS is available to qualified utilities and grid operators.