DeepJudge introduces Agent Handoff Protocol, with Harvey and Thomson Reuters among first to adopt. Open protocol enables users to move between AI platforms without starting fresh, carrying the context needed to continue their work. ZURICH, SWITZERLAND, August 13, 2026 / EINPresswire.com / - DeepJudge, the institutional intelligence platform for legal AI, today introduced Agent Handoff Protocol, an open protocol designed to enable context continuity across AI systems. Increasingly, people are moving between different AI products and experiences to complete their work. While existing protocols like the Model Context Protocol (MCP) enable systems to exchange information and perform specific actions, the broader context required to continue a task - including objectives, supporting materials, conversation history, and prior work - is often lost in the process. The Agent Handoff Protocol addresses this challenge by enabling AI platforms to transfer the user and the context needed to continue work from one system to another. Rather than rebuilding context each time they switch products, users can move between AI experiences while preserving the information and progress that led to the current point. For example, a lawyer researching a precedent question in DeepJudge can move into Harvey with the relevant context already in place, allowing the work to continue without re-uploading materials, recreating prompts, or rebuilding prior analysis. "No single AI experience will be the right one for every task," said Yannic Kilcher, CTO and Co-Founder of DeepJudge. "People should be able to use the AI tool that's best for what they need to do and take their context with them. That is the experience we built Agent Handoff Protocol to enable." DeepJudge developed Agent Handoff Protocol and is releasing it as an open protocol. Harvey, the leading legal operating system for legal and professional services, has announced an integration implementing Agent Handoff Protocol that is entering beta this month. Thomson Reuters is also supporting Agent Handoff Protocol, with additional details on their implementation and timing to follow in future announcements. Joel Hron, Chief Technology Officer of Thomson Reuters said, "The future of professional AI will not be defined by a single model, agent or application. Professionals will increasingly work across specialized AI experiences, and those systems need to work together without sacrificing the context, trust, and expertise required for high-stakes work. Open standards like Agent Handoff Protocol can help enable that interoperability, which is why Thomson Reuters is excited to support this effort and help shape what comes next." "The most capable legal workflows will draw on more than one specialized system. Agent Handoff Protocol lets a user move from Harvey into a partner's product and back without losing the thread of their work, while leveraging both products to their full potential. We're glad to be among the first to implement it," said Siva Gurumurthy, Chief Technology Officer at Harvey. As the institutional intelligence platform for legal work, DeepJudge is positioned to offer Agent Handoff Protocol as a shared resource rather than a proprietary advantage. The company invites other AI providers, specialist platforms, and law firms building AI solutions in-house to adopt the protocol and help shape its ongoing development. The Agent Handoff Protocol specification and implementation resources are available on GitHub. About DeepJudge DeepJudge is the core AI platform for legal professionals to harness their institutional intelligence. DeepJudge transforms institutional knowledge into structured, governed intelligence that enables legal teams to find and analyze information, uncover insights across matters, and apply what their organization already knows to new work. DeepJudge is trusted by leading law firms and in-house legal teams globally, including Holland & Knight, Cozen O'Connor, ArentFox Schiff, CMS, and Homburger, among others. To learn more, visit www.deepjudge.ai. Legal Disclaimer: EIN Presswire provides this news content "as is" without warranty of any kind. Australian News Journal do not accept any responsibility or liability for the accuracy, content, images, videos, licenses, completeness, legality, or reliability of the information contained in this article. If you have any complaints or copyright issues related to this article, kindly contact the author above.

Harvey announces partnership with Swiss legal AI intelligence platform DeepJudge. Collaboration will bring legal teams' previous work and decisions into Harvey's AI workflows 21 May 2026 Harvey and DeepJudge announce partnership Harvey has announced a partnership with Swiss legal AI intelligence start-up DeepJudge, with the aim bring law firm and in-house expertise into AI-powered legal work. DeepJudge's platform enables legal teams to integrate their previous work and decision making into Harvey's workflows, helping lawyers to research, draft and analyse with AI but combined with their own institutional knowledge. Harvey says the partnership addresses discrepancies within legal AI, in particular that the knowledge law firms have built up over decades of practice experience is often fragmented and difficult to collate in real-time. Winston Weinberg, Harvey CEO and founder, said: "DeepJudge knows your firm through every past matter, memo and negotiated position." He added that the partnership enables legal teams to "ground their work in prior expertise, and run their practice on a system that reflects how they actually operate". Advertisement Paulina Grnarova, CEO and co-founder of DeepJudge, said: "Legal AI has made remarkable progress on reasoning, and Harvey is a testament to that. "DeepJudge brings past work, decisions and institutional expertise directly into that reasoning, so that the resulting work reflects the judgement, standards and ways of working unique to each firm or legal department." Martin Durkin, partner at Holland & Knight, commented: "Together, they bring our firm's unique thinking into every document, turning AI into a true differentiator." Zurich-based DeepJudge was founded in 2021 by Grnarova, alongside chief operating officer Kevin Roth and chief technology officer Yannic Kilcher. They have all previously worked at Google, with Grnarova and Roth both having spells at Google Brain, while Kilcher was with Google AI Language. In November last year, DeepJudge raised $41.2m in an oversubscribed Series A funding round led by Silicon Valley venture capital firm Felicis alongside US technology investment management firm Coatue, at a $300m valuation. LAW OVER BORDERS COMPARATIVE GUIDES Artificial Intelligence Law Guide This second edition, written by leading AI legal specialists, provides answers and insight on how to integrate Artificial Intelligence into business operations, whilst working within the relevant law and guidelines in key jurisdictions around the world... | 1yr. Its seed funding round in June two years ago secured $10.7m, which that time was led by Coatue, with participation from notable angel investors such as Gokul Rajaram and Michele Catasta. Harvey has also announced the launch of Command Centre, which is designed to give users greater transparency into agentic insights and intelligence recommendations, and to compare how other organisations are using AI systems. Harvey chief product officer Anique Drumright told Legal IT Insider: "It's designed to help with adoption. Where you need to provide support or training, this is a single place where you can go and see what adoption is like. Often, that's very piecemeal. "Now, we're also providing anonymous benchmarking so our customers can see how they compare." Last month, UK Magic Circle firm Slaughter and May adopted Harvey's AI platform on a worldwide scale to support the firm's lawyers in areas including M&A, due diligence, regulatory research and document analysis.