A joint pilot program between the American CDMO Phlow and biotechnology company Enveda is advancing AI-driven active pharmaceutical ingredient (API) manufacturing process development.

The companies reported their efforts demonstrate that high-quality, internally generated reaction data can significantly improve certain AI-based predictions. Those data include clinical reaction kinetics, yields, and purity profiles.

How AI Impacts APIs

Ideally, Phlow and Enveda said, the data can compress development timelines from years to months. In fact, in three months, almost 20,000 unique reactions were generated. That effectively created one of the largest high-quality datasets of its kind.

What’s more, by training AI models on internally generated data, yield predictions were “substantially more accurate” than models trained on public datasets.

“This is about setting a new standard for pharmaceutical development and manufacturing,” said Eric S. Edwards, MD, PhD, Co-Founder and CEO of Phlow. “By combining Phlow’s advanced API development and manufacturing expertise with Enveda’s leading AI-driven insights and deep learning capabilities, we are creating a first-of-its-kind, innovative platform that predicts the optimal synthesis route the first time, every time, faster and more accurately than any other database. Together, we’re creating the future of how medicines are made with speed, precision, and resilience.”

Phlow and Enveda Meet the Moment

Enveda has been using AI to power its drug discovery platform for several years. The company injected $230 million into funding the process through June 2024.

Meanwhile, Phlow grew its analytical capabilities in April 2025, primarily by expanding its laboratory space in Richmond, Virginia.

“We’re helping to fortify the U.S. pharmaceutical supply chain with thoughtfully applied artificial intelligence and advanced manufacturing technologies,” Juan Piacquadio, Vice President and Chief Information Officer of Phlow, said at that time.