Senior Business Intelligence Analyst

Litera has partnered with Midpage to embed legal research capabilities into Lito, its AI legal agent, whilst releasing benchmark research highlighting limitations of general-purpose large language models for legal redlining tasks. The integration brings US case law and statutes from Midpage, trusted by over 200 law firms, directly into Lito's Microsoft 365 environment. Users can query documents against legal sources, check statutory compliance and generate case summaries without leaving Word or Outlook. Litera's internal research compared its purpose-built Compare tool against leading LLMs including Gemini 3, Claude Opus 4.5 and ChatGPT 5.2. Findings showed general LLMs struggled with non-text elements and accuracy declined significantly in longer documents, dropping to approximately 40-70% in 200-page tests. The company emphasised that whilst LLMs excel at research assistance, producing defensible legal redlines requires purpose-built technology.

Litera embeds legal research in Lito through Midpage partnership. Litera announced a new integration with Midpage to bring U.S. case law and statutes directly into Lito. The integration makes Lito the first legal AI assistant to combine generative AI capabilities, deterministic rules-based engines, proprietary firm intelligence, and Midpage's legal research tools within the microsoft 365 environment, where lawyers already work. Alongside the announcement, Litera is also presenting new internal benchmark research at Legalweek comparing how general-purpose large language models perform on complex legal redlining tasks versus purpose-built legal comparison technology. "Every legal AI tool has access to the same foundation models," said Adam Ryan, Chief Product Officer at Litera. "The difference is what surrounds them. Lito combines the best large language models with our rules-based engines, cutting edge firm intelligence data, and now deep legal research - all integrated where lawyers already work." The Midpage integration will deliver U.S. statutes and case law to Lito, adding to this powerful legal drafting environment and further expanding Litera's ecosystem of more than 60 integrations, including NetDocuments, iManage, Courtroom Insight, and UniCourt. By embedding trusted legal research sources within Lito, Litera continues to deepen the intelligence available directly inside everyday workflows. Through the Lito chat experience, users can select U.S. statutes or case law as sources to query against a document or a specific legal question. Practical use cases include checking whether an agreement complies with a particular statute, uploading a document alongside relevant legal authority for contextual analysis, or generating a case summary to share with clients - all without leaving Word or Outlook. Lito users on Litera One cloud packages will have access to legal research capabilities through this integration, with options to expand usage through a Midpage subscription. "Navigating case law has historically been so complex that it was really only done for complex litigation," said Otto von Zastrow, CEO of Midpage. "AI agents give every attorney the power of a big legal research team. The agent reads hundreds of cases and finds on-point precedents with quotes and hyperlinks. We're glad to bring this to tools like Lito that already have access to your documents and important context." Internal Research Examines AI Performance in Legal Redlining Alongside this announcement, Litera is sharing findings from internal Quality Engineering research evaluating how different AI approaches perform on complex legal redlining tasks, data that underscores why the architecture behind a legal AI tool matters as much as its capabilities. The research compared Litera Compare with leading general-purpose large language models, including Gemini 3, Claude Opus 4.5, and ChatGPT 5.2, across long-form legal documents containing tables, images, embedded objects, headers and footers, and other structural elements. The results illustrate a clear distinction: while large language models excel at research and drafting assistance, generating structured, defensible legal artifacts requires technology purpose-built for legal formatting standards and professional exchange. Key findings include: * Structural limitations: General-purpose LLMs were unable to generate usable redlines for non-text elements such as tables, images, embedded objects, headers/footers, and footnotes. * Accuracy declines with length: Even in short documents, general LLMs topped out at roughly 90% accuracy - a threshold that remains too low for legal work where a single missed change can carry significant consequence. In a 200-page document test, one model's text accuracy dropped to roughly 40%, with others declining to approximately 70%. * Description vs. redline: General-purpose LLMs can describe what changed in a document but cannot produce an actual redline or track changes file suitable for exchange with counterparties. Describing a change and delivering the legal artifact that lawyers need are fundamentally different outcomes. * Completeness over speed: While some models processed comparisons quickly, output reliability and coverage varied significantly across longer, more complex documents. Litera Compare powers redlining capabilities within Lito, enabling lawyers to produce accurate, industry-standard outputs while remaining embedded in their drafting environment. Together, the Midpage integration and Compare capabilities reflect Litera's broader approach: combining the intelligence of large language models with the precision of purpose-built legal engines, so lawyers get the best of both where it matters most. Litera will discuss both the Midpage integration and the research findings at Legalweek, March 9-12, 2026, in New York, NY, as part of broader conversations about how legal AI is evolving beyond experimentation toward measurable, reliable performance. Meet with Litera at Legalweek: Avaneesh Marwaha, CEO of Litera, will outline his vision "Accurate. Embedded. Fast. Raising the Bar for Legal Performance," Wednesday, March 11, 9:00 - 10:00 a.m., 4th Floor, Room 405.1 To learn more about how AI is transforming legal research and legal performance, reserve your spot for Litera's session at Legalweek here.

Litera expands Kira capabilities, unveiling the next generation of its market-leading AI contract intelligence. By Legal Futures Associate Litera Litera, a global leader in legal AI technology solutions, introduces enhanced Kira upgrades, driving the next evolution of its AI-powered contract intelligence solution. As deal activity increases and GenAI adoption accelerates across a growing market of legal tools, Kira helps legal teams analyze contracts at scale with the accuracy, governance, and collaboration required for high-stakes legal work. Trusted by 71% of the Fortune 100, Litera provides the proven, enterprise-grade foundation Kira builds upon - delivering reliable, governed AI for the most demanding legal environments. "While LLM technology has been a true game changer for contract review exercises, when LLM technology is paired with Kira's proprietary AI models, we are seeing incredible levels of accuracy and precision from simple natural language prompts," said Adam Ryan, Chief Product Officer at Litera. "The new iteration of Kira combines Litera's 30 years of legal expertise and a decade of AI refinement to bring GenAI to legal work with accuracy that teams can trust and governance they can control. By pairing GenAI with proven AI models and flexible oversight, Kira provides contract intelligence firms can rely on for their most critical matters." In high-stakes contract review, generic and pure GenAI tools are missing legal nuance and requiring extensive prompt engineering to produce reliable results. Kira addresses these challenges through a hybrid AI approach that combines GenAI with proprietary AI models trained on over 1 million legal contracts. This delivers consistent 90%+ accuracy while enabling legal teams to reduce review time, manage risk with confidence, identify and prevent contract value leakage, scale contract review workflows, and meet governance requirements without compromising reliability. Used across M&A, real estate, banking, finance, tax, and IP matters, Kira supports complex legal work where precision and consistency are essential. Law firms and legal teams are choosing Kira for: * Consistent, multi-layer accuracy: Hybrid AI combines GenAI with tested proprietary models to deliver reliable extraction of clauses, answers, and insights for high-stakes contract review. * Collaborative, easy-to-use workflows: Intuitive end-to-end workflows that simplify complex tasks - from organizing documents and tracking changes to managing reviews and exports - so teams can work together and scale effortlessly. * Two Powerful Tools: Lito for Drafting and Comparing in Word, Kira for High-Precision Analysis: Lito is included in the Kira subscription, and while each tool is fully standalone, they're designed to complement one another depending on the task. Use Lito for fast, structured everyday reviews in Word, Outlook and web, and rely on Kira when the stakes are high and require deeply accurate, high-precision contract analysis. * Flexible governance controls addressing varying compliance mandates: Legal teams can enable or disable GenAI at the project level to meet firm, client, or regulatory requirements without losing extraction capabilities and accuracy. * One Tech Partner, One Platform, One AI Agent: Leverage Kira together with Litera's complete ecosystem - drafting, transaction, knowledge management - to automate every step of a deal. In 2026, Litera plans to expand Kira's GenAI-powered capabilities to include: 1) Grid Chat for natural language querying across review data, 2) Generative Smart Fields with custom context grounded in verified extraction data, 3) A new wave of intelligent workflows designed to elevate both rapid-turn analysis and large-scale, collaborative reviews, while introducing forward-looking enhancements that deepen how legal teams surface, interpret, and act on their review insight.