프라마나 랩스, 270억 시드 투자 유치

As enterprises struggle to turn AI pilot programs into functional parts of their business, reliability has taken center stage. A new startup is hoping to solve that problem by drawing on the tools of mathematical formalization, combining one of computer science’s most reliable systems with one of its most chaotic. On Wednesday, Pramaana Labs announced $27 million in seed funding led by Khosla Ventures, with participation from Accel, Boldcap, Nexus Venture Partners, Premji Invest, and Unbound. Pramaana will focus on highly sensitive verticals like law, drug discovery, and tax preparation — where errors can be costly and reliability is at a premium. Deploying AI in those systems will require stronger protections against hallucinations and errors than we currently have. But as Pramaana co-founder and CEO Ranjan Rajagopalan sees it, they’re also uniquely suited to formalization. “It's like math in the sense that you have a lot of rules that you need to abide by,” Rajagopalan told TechCrunch, describing the rules of the tax code. “Once you have a codified version of it, the reasoning on top of it starts becoming deterministic.” Pramaana’s system still runs on a conventional LLM, giving it the flexibility to answer natural language questions and tackle complex problems that conventional computers can’t handle. But there’s a deterministic layer on top of that LLM ensuring the LLM’s work checks out. This combination of an LLM engine with deterministic verification is a popular setup ; Pramaana’s unique approach is to use the tools of formal verification — drawing on the open-source LEAN programming language used to verify mathematical proofs. There's real precedent for much of this work; Rajagopalan points to France's CATALA project , which formalizes much of the country's tax and benefit system into executable code. For each use case, Pramaana will build its own LEAN-style formal verification system, overseen by domain experts. For tax law, the company is working with former IRS commissioner Danny Werfel, while professors from IIT Delhi, IIT Madras, and UC Berkeley oversee the cybersecurity and drug discovery system. "The world's hardest problems are not unsolvable. They are unformalized,” says Rajagopalan. “Every domain where being wrong can cost someone their health, money, or freedom has rules.” Now, those rules just need to be codified. Topics AI , formal verification , reliability When you purchase through links in our articles, we may earn a small commission . This doesn’t affect our editorial independence. Russell Brandom AI Editor Russell Brandom has been covering the tech industry since 2012, with a focus on platform policy and emerging technologies. He previously worked at The Verge and Rest of World, and has written for Wired, The Awl and MIT's Technology Review. He can be reached at russell.brandom@techcrunch.com or on Signal at 412-401-5489. View Bio June 18 Los Angeles Get an inside look at what it takes to scale and succeed from leaders at Mach Industries, Founders Fund, and Shinkei Systems. Through candid fireside chats and high-impact networking, you'll walk away with valuable insights and new connections. REGISTER NOW Most Popular SpaceX to acquire Cursor for $60B in stock, days after blockbuster IPO Sean O'Kane The US government's Anthropic models ban was never about an AI jailbreak Zack Whittaker The AI layoff wave is becoming a powder keg Connie Loizos Amazon CEO reportedly raised Anthropic model concerns before government crackdown Anthony Ha The FBI built its own replica small town to simulate real-world cyberattacks Zack Whittaker Meta's months-old AI unit is a soul-crushing gulag, say the engineers stuck inside it Connie Loizos Jeff Bezos's Prometheus raises $12B to build an ‘artificial general engineer' for the physical world Marina Temkin