Legora launches legal research foundation for AI law

Legora has launched a new legal research foundation within its platform, combining comprehensive legal data with an AI-native ontology of law and a citator.

The move targets one of the hardest problems in legal technology: establishing what the law is and whether it still applies. Legora argues that artificial intelligence struggles with legal research when working across large volumes of unstructured material without a mapped view of how authorities rank, connect and change over time.

Legal research is the starting point for much of the work done by lawyers in law firms and in-house teams. That makes it a key test for AI tools in the profession, especially as legal teams assess whether software can be trusted to distinguish between binding and non-binding authorities, identify amendments and track whether a decision remains good law.

Its approach rests on two parts: gaining access to legal source material and creating a structured system for navigating it. Rather than relying on a model to interpret raw case law at scale, Legora is building what it describes as a full ontology of law that maps the hierarchy of authority, the meaning of legal propositions and temporal validity.

That structure sits beneath an AI-native citator, a research tool designed to show whether an authority remains current and binding. In established legal publishing, citators and related editorial systems have long been built through manual review by specialist lawyer-editors. Legora says it combines AI review with human oversight from former attorney-editors who set standards and handle quality control.

"We are building the operating system that agents run on inside legal organizations, and legal research is a critical part of that," said Max Junestrand, Chief Executive Officer and Co-Founder of Legora. "It is also the hardest thing in legal AI."

Legora argues that customers should not have to choose between access to data and the software used to work with it. That has become a recurring issue in legal technology, where firms and corporate legal departments often hold subscriptions to publisher databases but cannot easily use those resources inside newer AI tools.

"We don't believe our clients should have to choose between the best data and the best technology," said Melanie Brown, Head of Legal Data at Legora. "The frustration I hear most from clients is that they cannot access the data they already pay publishers for in the AI platforms they want to work in."

Data challenge

Legora works with publishers where commercial partnerships are available. In jurisdictions where that is not possible, it seeks source material through direct requests, physical scanning and other methods required by local legal systems.

That country-by-country process reflects the fragmented nature of legal information markets. Access to official reports, digitisation standards, anonymisation rules and licensing practices vary widely between jurisdictions, creating practical barriers for technology groups trying to assemble multinational legal datasets.

"It's a different problem in every country," Brown said. "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."

Data access alone does not solve the reliability problem, Legora argues. AI systems cannot reason dependably across hundreds of millions of documents and may struggle even when a single matter involves only a few thousand materials. That means source selection and relationship mapping must happen before the reasoning step begins.

Failure points

Its legal research work uses technology from the acquisitions of Qura and Wexler. Legora says those tools help convert large document collections into structured datasets that software agents can use more reliably.

Arvid Winterfeldt, who leads Legal Research at Legora and was Co-Founder and Chief Executive Officer of Qura, said the company has identified a wide range of recurring errors in AI-led research.

"We have cataloged more than 50 distinct ways AI fails at legal research," said Arvid Winterfeldt, who leads Legal Research at Legora and was Co-Founder and Chief Executive Officer of Qura, the legal research company Legora acquired earlier this year. "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. A passage can look perfectly relevant in isolation and have been made obsolete by a later case."

Brown said advances in AI have changed the economics of reading and classifying legal text at scale, a task once associated with decades of manual editorial labour inside legal publishing houses.

"That's what AI changes," Brown said. "For the first time, having someone, or something, read 60 million pages of case law is no longer prohibitive."

Legora says more than 100,000 legal professionals use its platform across more than 1,800 law firms and in-house legal teams in over 50 markets. The new research layer is intended to sit beneath other work carried out in the system, making legal research not a separate product line but part of the wider operating structure the company is building for legal organisations.