Two teenage founders came up with an idea in Y Combinator co-founder Paul Graham’s backyard that no one in the agriculture sector wanted — an AI model to help design better pesticides. By the time he left, he had a new business model, a new company, and finally Graham’s support.
Now, that reimagined company – bindwell – has raised $6 million in a seed round, co-led by General Catalyst and A Capital, with a personal check from Graham himself. Instead of selling AI tools to older agrochemical giants, the startup is using its own models to design new pesticide molecules in-house and licensing the IP directly — a change in strategy aimed at modernizing a legacy industry that’s still dominated by decades-old chemistry.
pesticides are used in agriculture doubled in the last three decadesAs yet 40% of global crop production According to the United Nations Food and Agriculture Organization, there are still losses from pests and diseases every year. As pests evolve and develop resistance, farmers are forced to use increasing amounts of chemicals to maintain the same yield – a cycle that damages ecosystems and exacerbates resistance even further. Regulatory pressure is increasing, but most agrochemical companies still rely on tweaks to older compounds. Bindwell is betting that AI can break the cycle by discovering entirely new, more targeted molecules – ones tailor-made for modern challenges.
Founded in 2024 by 18-year-old Tyler Rose and 19-year-old Navve Anand, Bindwell has adapted AI-led drug discovery technologies to agriculture with the goal of accelerating the identification and testing of new pesticide molecules.
Bindwell began as a research project in the fall of 2023, when Rose and Anand were students in the Wolfram Summer Research Program. They initially focused on a drug discovery AI model called PLAPT, which involved binding affinity prediction – work that was later cited in a Nature Scientific Reports paper on cancer therapeutics. In 2024, they began exploring how the same approach could be applied to pesticides.
Both founders had personal knowledge of this problem. Rose learned about the challenges of pest control from her aunt, who farms in China. Anand’s family owned farms in Delhi, where he saw firsthand how limited pesticide options affected crop yields.
“Agriculture has been on our minds,” Rose said in an interview. “It led to the realization that we could use the same techniques that have been successful in drug discovery. We could bring it to pesticide discovery, because the biochemistry is the same, but pesticides are a bigger problem, and I think that’s not what most people are focused on.”
techcrunch event
san francisco
,
October 13-15, 2026
Rose and Anand entered Y Combinator’s Winter 2025 batch with a plan to build AI models and sell their access to major agrochemical companies. But they didn’t gain any traction – most industry players were reluctant to adopt AI as a core part of pesticide detection. In between shows, he was invited to Paul Graham’s house, where he talked to him on the back patio for about 45 minutes.
After hearing about their challenges, Graham suggested a different approach: Instead of selling the tools, they could use their own models to discover new pesticide molecules. That conversation marked the beginning of Bindwell’s current direction.
He later added, “(Bindwell’s) founders will probably do just fine.” Posted On X. “They’re smart and they have a good idea.”
Bindwell has developed its own AI suite designed to reduce hallucinations – a common issue where models produce unreliable or unsupported output. The software includes FoldWell, a structure prediction model, a fine-tuned version of DeepMind’s AlphaFold, which is used to identify target protein structures. It also includes PLAPT, an open-source protein-ligand interaction model capable of scanning every known synthesized compound in less than six hours, and APPT, a protein-protein interaction model for biopesticide screening that outperforms existing tools by 1.7× on affinity benchmark v5.5. Additionally, the suite includes an uncertainty quantification system that lets you know when results are reliable and when more data is needed.
“Since we’re not selling AI models, we’re not competing with companies that sell models,” Rose told TechCrunch.
Together, Bindwell’s models can analyze “billions” of molecules, the startup said, and deliver performance up to four times faster than DeepMind’s AlphaFold 3.
“The way most pesticide discovery is done right now is not target-based,” Rose said. “Entomologists and chemists suggest different compounds, then test them on insects. You often need to synthesize and test thousands of chemicals to check efficacy, which is expensive. With our AI model, you are able to simplify the problem to a single protein.”
AI helps identify proteins that are unique to a specific insect but are absent in humans, beneficial insects or aquatic organisms such as water fleas.
“Once you’ve got those proteins, you can design something that will bind to them and stop them from working,” Rose said.
Bindwell is currently testing the efficacy of his AI-generated molecules in his laboratory in San Carlos. It is also working with a third-party partner to further validate the models, though Rose declined to share details.
Rose said the startup is in early discussions with several global agrochemical firms, with its first partnership deal expected to close soon. “A year from now, we want to have our own licensing deals with some of these companies,” he said. Bindwell has also started talks with stakeholders in India and China to conduct field trials.
The startup currently has a team of four people, and also works with external contractors for molecule synthesis.
Bindwell’s seed round also included SV Angel partnering Graham. Before joining Y Combinator’s Winter 2025 batch, the startup raised a pre-seed round from Character Capital.
