Inductive Bio launched Indy, an AI chemistry assistant, available to partners now. Inductive's medicinal chemists, computational chemists, and DMPK scientists built Indy for their work inside partner programs, where it has doubled the team's productivity. Indy gives every scientist an AI chemistry assistant that has been trained from some of the best drug hunters in the world to work with a program's data and computational tools (including Inductive's benchmark-winning ADMET and PK models) to increase the rigor of every decision made every day on every program.

The constraint on a discovery program is rarely how quickly scientists can come up with new ideas for molecules. It is the quality of the day-to-day analyses and decisions, big and small, that add up over years to the success or failure of a drug program. Do I trust the data from this assay? What does the new data tell us about SAR? What design strategies will get me closer to my TPP? Are my synthetic resources focused on the right targets? What's the fastest route to test my design hypothesis? Are any of our synthetic targets falling behind? Getting the right answers to these questions takes up the majority of medicinal chemists' time, while getting the wrong answers can waste months of a team's time.

Indy removes this operational bottleneck from drug discovery, increasing the rigor of every decision a medicinal chemist makes. Indy parses CRO reports, QCs every dose-response curve, interprets historical SAR to discern trends, runs generative chemistry algorithms, sets up FEP calculations, and generates project update slides for your next meeting. Scientists get more time for the high-impact work only they can do, enabling higher-quality program decisions with greater confidence.

In a head-to-head comparison published today, Indy outperformed Claude Opus 5 and GPT-5.6 Sol on 84 dose-response curves from real programs. Indy had an accuracy of 89%, compared to 39% for GPT-5.6 Sol and 48% for Claude Opus 5, even when Claude and GPT were told to use the highest levels of effort.

"We have incorporated Indy into a number of workflows, including data QC, SAR table construction and analysis, and synthesis queue management," said Nicholas Perl, PhD, head of chemistry at Anvia Therapeutics. "Indy surfaces patterns in the data that help us make better decisions, and it lets me spend less time maintaining slides and more time driving scientific strategy."

"We trained Indy on the tasks that take medicinal chemists' time but not their creativity," said Josh Haimson, co-founder and CEO of Inductive Bio. "The result is an assistant that can double a chemist's productivity while fitting seamlessly into their existing workflows."