Legora news and product updates

Ontological Legal Research is now live in the US, after Legora described the approach in September. It pairs primary law Legora collects directly, including slip opinions from court websites within 24 to 48 hours, with a prebuilt ontology linking defined terms to the cases that interpret them, overruled cases to the decisions that overruled them, and rules to their exceptions. Legora says the structure makes its Agent 40% faster on an internal set of thousands of research questions, and its AI native citator comes next.

Buyer relevance. Research grounded in how authorities relate to each other, not just text similarity, is a direct answer to AI citing overruled law. The 40% figure measures speed on Legora's own test set, so buyers should ask for accuracy results too.

Legora launched Intake, available now in Slack. Employees mention Legora in a channel, the Legora Agent asks for any missing details in the thread, and the request goes to the right legal team as a tracked task with an owner and a due date. The Agent then prepares the work from the team's own Skills, playbooks and precedents, and a lawyer reviews every output by default, except for request types the team approves in advance, such as a standard NDA, which the Agent can complete and return on its own.

Buyer relevance. In house teams now set, request type by request type, when the Agent may answer the business without a lawyer, so buyers should check who controls that setting and how it is logged. Intake runs only in Slack for now; Legora says Microsoft Teams, email and MCP are planned.

Legora released Skills to all customers: Markdown instruction files, which can bundle templates and examples, that teach the Legora Agent a team's standards, processes and preferences. The Agent applies a relevant Skill automatically or a user calls one with a slash, and a library of more than 250 Skills ships with the feature. Admins can restrict sharing, recipients must install a shared Skill before it runs, and matter permissions still apply.

Buyer relevance. Firms can make the Agent follow house style and practice group playbooks without retyping instructions in every prompt. Install on share and admin limits keep one lawyer's Skill from quietly changing how the whole firm's Agent behaves.

Legora connected to iManage Cloud. Users link an iManage matter to a Legora project, and the Legora Agent can search it by client, matter, author, date or the firm's own custom fields, then browse and preview files. Edits made in Word show as tracked changes and go back to iManage as a new version or a new document only when the user chooses, and each user connects their own iManage account so existing access rights apply.

Buyer relevance. Firms on iManage can use Legora on live matter files without exporting them into a separate workspace. Because the Agent never saves on its own and each user's iManage permissions carry over, ethical walls set in the DMS still hold. The Legora team enables the connector for each organisation.

Legora released a plugin for ChatGPT Enterprise that brings Legora's grounded legal answers into the ChatGPT interface. OpenAI also named Legora as one of the API customers that will build on Astra for Law.

Buyer relevance. Legora is now on both sides of OpenAI's legal launch: a plugin inside ChatGPT and a customer building on the model underneath. Firms standardizing on ChatGPT Enterprise should ask which Legora capabilities the plugin exposes, and which still require the Legora platform itself.

Legora is rebuilding the research layer of its platform on a full ontology of the law and an AI native citator, built with technology from its Qura and Wexler acquisitions. The ontology maps how authorities rank and relate, including amendments, holdings versus dissents and temporal validity, and a team of former publisher attorney editors sets and audits the citator standard. It is in limited beta now, with general availability planned for Q4.

Buyer relevance. Citator status is the part of legal research AI buyers have had to take on faith, and it is where the sanctions cases came from. Legora says it has cataloged more than 50 distinct ways AI fails at legal research, which hands buyers a checklist to test any research tool against. Until Q4, treat this as a beta to evaluate, not something to rely on in a filing.