Bindwell
We're building better pesticides using AI. The agrochemical industry is stagnant, it's time for a change. Backed by Y Combinator, General Catalyst, SV Angel, A.Capital, Character, Paul Graham, and others.
The founders [of Bindwell] will probably do alright. They're smart and have a good idea. Paul Graham, on X
Team
We're Tyler Rose (Wolfram Research) and Navvye Anand (Caltech), a scrappy duo of engineers who met at the Wolfram Summer Research Program in June 2023. Both with backgrounds in research. United by our passion for tackling global problems, we dropped out of high school / college and started Bindwell to transform the agrochemical industry.
Problem
Pesticides are getting worse over time: their usage per acre has doubled since 2000, yet losses due to pests have stayed around the same. Insects are evolving resistance faster than the industry can do R&D. It's the only area of biotech that's getting worse over time, not better.
AI for biology is stalling: models have raced ahead in math and code over the last few years. Biology has barely moved, and the gap keeps widening. It is not for lack of compute or attention.
Biology has no verifier: math has proof checkers and code has test suites: cheap, automatic verifiers that can tell a model whether it was right, millions of times over. Nothing does that for a molecule. Without a verifier there is no signal to train against, and progress stalls.
Solution
So we built the verifier.
Our 8,000 square foot automated lab runs the full design–make–test loop without human hands, returning hard experimental ground truth at a scale a manual lab cannot reach. Every molecule our models design gets measured, and every measurement becomes training signal.
Training models on verifiable domains like math and code made them better at everything, including tasks nobody can verify. We're doing the same for biology, and it already seems to be working. Scaling computation and data rather than relying on manual design is the fastest path to new molecules, and follows the teachings of Richard Sutton's The Bitter Lesson.
We're starting with pesticide discovery, where the need is most urgent: our first pesticide targets the invasive pest Spodoptera frugiperda. From there we're scaling the same approach to all of molecular discovery.
Careers
If you're an excellent engineer interested in developing foundational ML models to solve molecular design, we'd love to hear from you. Reach out to us at careers@bindwell.ai.
News & Press
- Defeating pests with AI models: Our first-principles approach
- Teen founders raise $6M to reinvent pesticides using AI
- Introducing APPT: Affinity Protein–Protein Transformers
Contact us
We're always glad to hear from industry professionals, investors, potential collaborators, and anyone else with an interest in what we're doing.
You can reach us
- by email at founders@bindwell.ai;
- by phone at +1 (202) 873-0009;