The U.S. Food and Drug Administration (FDA) has unveiled Elsa, a generative AI tool aimed at enhancing efficiency across its workforce — from scientific reviewers to field investigators. 

Elsa is powered by large language models and is designed to assist FDA staff with a range of tasks including reading, writing and summarizing. 

It can quickly summarize adverse events to aid in safety profile assessments, streamline label comparisons, and even generate code to support the development of databases for nonclinical research. 

The tool is developed in a secure GovCloud environment, which enables employees to access internal documents without using or training on sensitive industry data.

“Today marks the dawn of the AI era at the FDA with the release of Elsa. AI is no longer a distant promise but a dynamic force enhancing and optimizing the performance and potential of every employee. As we learn how employees are using the tool, our development team will be able to add capabilities and grow with the needs of employees and the agency,” FDA Chief AI Officer Jeremy Walsh said.

Elsa is already streamlining clinical protocol reviews, accelerating scientific evaluations, and improving inspection targeting.

As the tool evolves, the agency plans to expand AI integration into additional workflows — ranging from data processing to advanced generative AI capabilities — to further strengthen and streamline its mission-driven operations.