Bright key facts / Deployed
Two weeks of grid preparation, reduced to hours.
Duke Energy says an AWS agentic workflow reduced data preparation for interconnection studies from two weeks of manual work to hours by coordinating existing models and scripts.
- AI’s role
- Agents orchestrated existing engineering tools and data preparation; engineers retained final decisions.
- Documented result
- Duke reports reducing preparation from two weeks to hours. LBNL separately reports more than 2,000 GW of generation and storage seeking interconnection at the end of 2025.
- Important limitation
- The time reduction is partner-reported and not independently audited.