
The Brief:
Legora launches a new legal research engine built on comprehensive data, a full map of how the law connects, and an AI-native citator.
The build draws on tech from its Qura and Wexler acquisitions, aimed at making AI legal research something lawyers can actually trust.
Legora has rebuilt legal research from the ground up.
The agentic legal platform has launched a new foundation for its research tool —comprehensive legal data, a full ontology of law, and an AI-native citator.
The idea is simple. AI has always struggled with legal research because it doesn’t understand how legal authorities rank against each other, like which cases are binding, which are outdated, and which overrules another. Legora’s new build tries to fix that by mapping those relationships upfront.
“We are building the operating system that agents run on inside legal organizations, and legal research is a critical part of that,” said CEO and co-founder Max Junestrand. “It is also the hardest thing in legal AI.”
There are two parts to the fix. First, getting hold of the actual legal data. Second, building the tech to make sense of it.
On data, Legora partners with publishers where it can, and goes direct where it can’t, through manual requests, physical scanning, or whatever else the jurisdiction demands.
“It’s a different problem in every country,” said Head of Legal Data Melanie Brown. “In the US, access to citable case law is constrained by the companies that own the official reports and won’t sell a digital feed. In Germany, the challenges are digitization and anonymization. But there is always a way, and we’re doing whatever it takes to bring together every data type in over 100 countries around the world. We are bringing all the world’s legal data into Legora."
Having the data isn’t enough on its own though. An AI agent can’t just read hundreds of millions of documents and figure out what matters. Someone, or something, has to sort and tag the relationships between them first.
That’s where the ontology and citator come in, built using tech from Legora’s acquisitions of Qura and Wexler.
“We have cataloged more than 50 distinct ways AI fails at legal research,” said Arvid Winterfeldt, who leads Legal Research at Legora and co-founded Qura. “AI cites a rule and misses the amendment that changed it. It quotes a dissent as the holding. It puts a non-binding agency decision on a par with a Supreme Court case.”
Legora has put together a team of attorney editors, veterans of publishers’ navigation tools, to set the standard and quality-check the new citator.
The ontology is in limited beta now, with a full rollout planned for Q4.
Source: Legora