Pramaana Labs raises $27M seed round from Khosla Ventures to bring formal verification to AI
Pramaana Labs has raised $27 million in seed funding to develop AI systems that combine large language models with formal verification, focusing on sensitive domains like law, drug discovery, and tax preparation.
Pramaana Labs, a startup aiming to solve AI reliability issues, announced a $27 million seed round led by Khosla Ventures, with participation from Accel, Boldcap, Nexus Venture Partners, Premji Invest, and Unbound.
The company will focus on highly sensitive verticals such as law, drug discovery, and tax preparation, where errors can be costly and reliability is paramount. Pramaana’s system runs on a conventional large language model (LLM) but adds a deterministic verification layer to ensure the LLM’s outputs are correct.
Its unique approach uses formal verification tools based on the open-source LEAN programming language, commonly used to verify mathematical proofs. For each use case, Pramaana will build its own LEAN-style verification system overseen by domain experts. In tax law, the company is working with former IRS commissioner Danny Werfel, while professors from IIT Delhi, IIT Madras, and UC Berkeley oversee cybersecurity and drug discovery systems.
Co-founder and CEO Ranjan Rajagopalan says, “The world’s hardest problems are not unsolvable. They are unformalized.” He notes that every domain where being wrong can cost health, money, or freedom has rules that just need to be codified. The approach draws inspiration from France’s CATALA project, which formalizes the country’s tax and benefit system into executable code.
