At Undermind, we're building a search engine that can handle extremely complex questions. It’s geared at experts, like research scientists and doctors, who need to find very specific resources to solve high-stakes problems. We’ve rebuilt search from the ground up to address this. Our new approach employs high-quality LLMs to adaptively explore a database, mimicking how a human researcher carefully discovers information. This approach dramatically outperforms (by 10-50x) traditional keyword search and other modern AI-based retrieval methods. Our first target users are the 50 million researchers searching for scientific literature on PubMed and Google Scholar every month. We’ve launched and have users paying us $200-$1000 per seat per year, from fields like medicine, ML, biotech, finance, and more. Our techniques in the future can port to even broader use cases and databases in law/consulting/finance.
Tom is the co-founder and CTO at Undermind. He studied physics at Princeton, then did his PhD in quantum physics at MIT. His thesis was recognized by the American Physical Society as one of the top 4 theses in the field of atomic physics in 2022, and he has published 10 papers in the field, including two in Nature and Science. Tom has deep expertise in building and deploying complex systems.
Josh is the co-founder and CEO at Undermind. He has research experience in gravitational-wave astrophysics (LIGO), particle physics (CERN), atomic physics, and quantum information science. He did his PhD at MIT studying quantum computing architecture design and inventing techniques for generating entangled multi-particle states using atom-light interactions, with 3 patents pending and 6 peer-reviewed publications.
Finding the right resources to solve problems is crucial for doing impactful research. However, researchers often need to find really complex information, and tools like PubMed and Google Scholar simply aren’t up to the task. They only work for simple, short keyword phrases, and it often takes hours to sift through the (mostly irrelevant) results.
We rebuilt search from the ground up to make it work really well for complex questions. Our AI agent mimics how a human researcher carefully discovers information. It spends a few minutes carefully looking through hundreds of papers for you and adapts based on what it finds to uncover everything. Ultimately Undermind’s results are 10-50x better than traditional keyword search engines.
Just write down your complex research topic, describing exactly what you want, as if to a colleague. After 2-3 minutes, Undermind will give you the precisely relevant articles you need.
We’re scientists ourselves, and we’ve spent a lot of time looking through scientific literature. We’ve personally experienced those “aha” moments - when you realize you could have saved 3 months of work if only you knew about that one paper earlier! So, our goal isn’t to save you a few minutes of searching yourself; it’s to make it easy to find the solutions that can drastically improve your overall research plan and trajectory.