Bindwell

We're building better pesticides using AI. The agrochemical industry is stagnant, it's time for a change.
Backed by Y Combinator, 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

Try our screening platform Get in touch Read our blog

The team

We’re Navvye Anand (Caltech) and Tyler Rose (Wolfram Research), a scrappy duo of engineers who met at the Wolfram Summer Research Program in June 2023. We’re from India and China, respectively, and both grew up visiting farmlands in our countries. United by our passion for tackling hard problems, we dropped out of college and started Bindwell to transform the archaic agrochemical industry.

We’re joined by Max Niederman, a prodigious hacker and open source contributor who dropped out of a math degree at Reed College. Max is relentlessly curious about everything from graphic design to robotics, and his passion for solving challenging problems made him a perfect fit for our team.

The problem

Pesticides are failing us: Their usage has doubled since 2000, even though farmland has decreased. Yet, we still lose 20-40% of crops to pests.

Resistance makes things worse: Pests evolve resistance, forcing farmers to use even more pesticides to get the same results. This creates a vicious cycle of increasing resistance and collateral damage.

Innovation is stagnant: Since the 2010s, fewer than 40 new active ingredients have been introduced. Most "new" pesticides are just minor tweaks of existing chemicals.

Industry left behind: AI has revolutionized drug discovery; pesticide discovery is overdue for the same transformation because the underlying biochemistry is similar.

Making better pesticides is hard: The ideal pesticide kills only the target pest and nothing else—current solutions fail at this.

Our solution

We use AI to build better pesticides.

Because pesticide discovery is a search problem, speed is key: In mere seconds, our AI models give us biological assays that would have traditionally taken days—completely changing the game for pesticide discovery.

We've built these AI models so far:

We’re currently mapping druggable proteins in select harmful species that are notoriously difficult in the industry in order to find candidates with high specificity.

Today

We have state-of-the-art models for predicting binding affinity of protein–ligand and protein–protein complexes, as well as our own AlphaFold replacement that's 4× faster. You can see a live speed comparison demo below, or try our unified screening and structure prediction demo. Many of our models are open source, so you can take a look at the code on our GitHub.

Bindwell

Traditional