According to Dynamic Beating monitoring, Pramaana Labs, a startup dedicated to bringing mathematical formal verification into AI, has announced the completion of a $27 million seed round. The round was led by Khosla Ventures, with participation from Accel, BoldCap, Nexus Venture Partners, Premji Invest, and Unbound. The funding will be used to build a deterministic verification layer for highly sensitive industries with zero tolerance for errors, such as legal, drug development, and tax compliance.
Pramaana Labs' underlying system still operates on a traditional LLM to maintain flexibility in handling complex problems and natural language. However, its core innovation lies in building a layer of deterministic verification on top of LLM. This mechanism draws inspiration from the open-source LEAN programming language used to verify mathematical theorems and codifies industry-specific rules.
To build a LEAN-style formal verification system for different vertical industries, Pramaana has enlisted a large number of domain experts for supervision and endorsement. In the tax domain, the company is collaborating with former IRS Commissioner Danny Werfel; while in cybersecurity and drug development systems, the initiative is led by a team of professors from the Indian Institutes of Technology (IIT) Delhi and Madras, as well as the University of California, Berkeley.
