Pramaana Labs has raised a $27M seed round led by Khosla Ventures to apply formal verification techniques to AI systems in high-stakes domains like law, drug discovery, and tax preparation. The startup combines conventional LLMs with a deterministic verification layer built using the LEAN formal proof language, aiming to eliminate hallucinations and errors where reliability is critical. Domain experts including former IRS commissioner Danny Werfel and professors from IIT Delhi, IIT Madras, and UC Berkeley are involved in building domain-specific verification systems. The approach draws inspiration from France's CATALA project, which formalizes tax and benefit rules into executable code.
126 Impressions