Pramaana Labs raises $27M seed round from Khosla Ventures to conduct formal validation of AI

As companies struggle to turn AI pilots into functional parts of their business, reliability has taken center stage. A new startup hopes to solve this problem by relying on mathematical formalization tools, combining one of the most reliable computer science systems with one of the most chaotic computer science systems.

Wednesday, Pramana Laboratories It announced a $27 million seed round led by Khosla Ventures, with participation from Accel, Boldcap, Nexus Venture Partners, Premji Invest and Unbound.

Pramaana will focus on highly sensitive sectors such as law, drug discovery, and tax preparation – where mistakes can be costly and reliability is at a premium. Deploying AI in these systems will require stronger protections against hallucinations and errors than we currently have. But as Ranjan Rajagopalan, co-founder and CEO of Pramaana, sees it, they’re also uniquely suited to formalization.

“It’s like mathematics in the sense that you have a lot of rules that you need to adhere to,” Rajagopalan told TechCrunch, describing the rules of the tax code. “Once you have a codified version of it, the logic behind it starts to become deterministic.”

Pramaana’s system still runs on a traditional LLM, giving it the flexibility to answer natural language questions and tackle complex problems that traditional computers can’t handle. But there is a deterministic layer on top of the LLM that ensures that the LLM is working.

This combination of an LLM engine with deterministic verification is Popular setting; Pramaana’s unique approach is to use formal verification tools — drawing on the open source LEAN programming language used to verify mathematical proofs. There is real precedent for much of this work. Rajagopalan points out French Catala projectwhich formalizes much of the country’s tax and benefits system into enforceable law.

For each use case, Pramaana will build its own formal LEAN-style validation system, overseen by domain experts. For tax law, the firm is working with former IRS Commissioner Danny Werfel, while professors from IIT Delhi, IIT Madras and UC Berkeley oversee the cybersecurity and drug discovery ecosystem.

“The world’s most difficult problems are not unsolvable,” says Rajagopalan. “They are informal.” “Every area where making mistakes can cost someone their health, money or freedom has rules.”

Now, these rules just need to be written down.