Undermind logo

UndermindA search engine for complex questions

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.

2024-06-17
Active
Early
S24
2
B2B
United States of AmericaAmerica / Canada
Undermind screenshot
More About Undermind

Undermind - AI-Powered Scientific Research Assistant

Radically better research, radically faster

Key Features

  • Intelligent Assistant: Acts like a personal research assistant, providing the best knowledge and solutions.
  • Complex Topic Handling: Understands and processes incredibly complex topics as if conversing with a colleague.
  • Accurate Results: Delivers precise papers with clear explanations on their relevance.
  • Comprehensive Discovery: Reads and adapts through hundreds of papers, ensuring thorough research.
  • Brainstorming Copilot: Assists in identifying the most important research questions.

Use Cases

  • Quantum Computing: Research on shuttling trapped ions in three dimensions for quantum computing applications.
  • Artificial Intelligence: Find recent papers on AI for managing coding databases, including metrics and architecture.
  • Information Science: Study the quantitative effect of search latency changes on Google Scholar usage rates.
  • Sociology: Explore the evolutionary purpose of romantic love in humans, focusing on parental investment and cooperation.
  • Neuroscience: Investigate the molecular mechanisms underlying Hebbian learning and the involvement of hormone-like chemicals.
  • Atomic Physics: Discover papers on laser cooling to Bose-Einstein condensation without using evaporative cooling.

Pricing

Undermind offers various pricing plans tailored to individual researchers, academic institutions, and corporate teams. Detailed pricing information is available on the website.

Teams

Undermind was founded by two quantum physics PhDs from MIT, bringing decades of deep research experience to the development of next-generation AI-powered search algorithms. The team is dedicated to supporting researchers with tools that augment their capabilities in the age of AI-powered scientific discovery.