In an era where technology continues to revolutionize traditional industries, the legal sector is poised for significant change through the advent of event contract markets. Von Wooding, founder of legal AI startup Counsel Stack, believes these markets are set to influence legal predictions and outcomes, emphasizing the role of legal research in this evolving landscape. As legal professionals increasingly seek to understand trends and patterns in case law, Wooding said the emergence of event contract markets, such as Kalshi and Polymarket, will change the dynamics of legal predictions. "Legal research helps you see where a case is probably heading. When you dig through enough opinions, you start to notice how judges handle recurring issues, which arguments survive contact with precedent, and where the real friction points sit," he said. According to Wooding, while legal outcomes may never be entirely predictable, the right analytical frameworks can significantly enhance the accuracy of predictions. “Patterns show up and trends emerge. Legal outcomes are not perfectly predictable, but with the right heuristics they are not a coin toss either. Attorneys understand this," Wooding said. "This nuanced understanding gives legal practitioners an edge when navigating complex cases and various judicial interpretations. With the advent of platforms that allow betting on the outcomes of major cases, attorneys will have access to novel data that can refine their predictions. "When prediction markets form around major cases, the advantage will go to whoever understands the facts and underlying political pressures," Wooding notes. “Arguably most importantly, deeper patterns in the doctrine play a crucial role in shaping these outcomes.” Wooding speaks as his company prepares for its next step following Counsel Stack's exceptional performance in the VAILS Legal AI Report in Q3 2025. Wooding's platform secured best overall performance, as well as top scores in accuracy, authoritativeness and appropriateness. The integration of event contract markets into the legal sphere signifies a shift toward leveraging data analytics as a mechanism for understanding judicial behavior. "Research becomes a tool for reducing uncertainty," Wooding asserts. "It gives one a clearer sense of the range of outcomes and why one trajectory makes more sense than another." Analysts report this perspective highlights the potential for enhanced decisiveness among legal professionals, empowering them to make informed decisions based on data-driven insights.

Counsel Stack, the Pittsburgh-born startup and Brown and White Ventures portfolio company, outperformed every other legal AI startup to enter the nation's foremost independent legal research survey. Those results were reported in the Vals Legal AI Report (VLAIR), which extended its original survey and evaluated how AI products perform on legal research tasks. It measured performance with respect to a lawyer control group, known as the Lawyer Baseline. Counsel Stack joined early industry leaders Alexi, Midpage, ChatGPT and one other significant, unnamed company in the survey. Vals reported: "Counsel Stack demonstrated strong performance across all evaluated criteria, achieving the highest scores among all participants with 81% accuracy, 77% authoritativeness, and 71% appropriateness, resulting in a 78% aggregate weighted score." The Vals assessment measured the participants’ ability to respond to 200 U.S. legal research questions, distributed across a range of question types typically encountered in private practice. The study established a scoring rubric taking into account prior studies and industry feedback. In the end, Vals evaluated responses using three weighted criteria. · Accuracy: whether the response is substantively correct with no incorrect elements (50% of average weighted score) · Authoritativeness: whether the response is supported by citations to relevant and valid primary and/or secondary law sources (40% of average weighted score) · Appropriateness: whether the response is easy to understand and could be immediately shareable with colleagues or clients (10% of average weighted score VLAIR reported that, based on evaluation results from its survey, Counsel Stack demonstrated several notable capabilities: Highest overall performance: Achieved the top score across all three evaluation criteria (accuracy, authoritativeness, and appropriateness) among all participants in the study, including other legal AI products, generalist AI, and the lawyer baseline. Superior accuracy: At 81% accuracy, Counsel Stack tied for the highest accuracy score, demonstrating strong capability in providing substantively correct responses with minimal misinterpretations or factual errors. Strong source citation: Scored 77% on authoritativeness, leading all participants in identifying and citing relevant and valid primary law sources, an essential differentiator for legal AI products over generalist alternatives. Comprehensive legal coverage: Successfully provided responses to 196 of 200 questions, with only 4 technical timeout issues, demonstrating broad coverage of U.S. legal research questions across federal and state jurisdictions. Specialized LLM architecture: Built with multiple specialized LLMs specifically designed for legal research, enabling the product to handle the unique requirements of legal source identification and citation. Consistent quality: Outperformed the lawyer baseline by 9 percentage points overall (78% vs 69%), demonstrating the ability to augment and enhance legal research capabilities for practicing attorneys. Superior to generalist AI on sources: Achieved significantly higher authoritativeness scores compared to generalist AI products, reflecting the value of access to proprietary legal databases and specialized training on legal sources. Founded in 2023, Counsel Stack offers multiple specialized LLMs for legal research, document review and client communications. In the VLAIR legal research study, their research product achieved the highest performance across all evaluation criteria, ranking first among all participants including legal AI products, generalist AI, and the lawyer baseline. Brown and White Ventures made a $200,000 investment in Counsel Stack in 2025.

Since turning in the top performance in every measurable and securing best overall score in the VAILS Legal AI Report, Counsel Stack has spent the days since the study's release sharing how it scored best in accuracy, authoritativeness and appropriateness. "Counsel Stack's win across all metrics reflects genuine superiority in the criteria that matter: substantive accuracy, citation quality, and legal authoritativeness. This wasn't a self-reported benchmark or a controlled demo—it was an independent, double-blind evaluation where quality alone determined the outcome," said founder and CEO Von Wooding. Counsel Stack delivered top VAILS score in all three assessment criteria (accuracy, authoritativeness, and appropriateness) among all participants in the study, including other legal AI products, generalist AI, and the lawyer baseline It also registered what the report called "superior accuracy," what VAILS termed "strong capability in providing substantively correct responses with minimal misinterpretations or factual errors." Wooding also celebrated Counsel Stack leading all VAILS participants in authoritativeness by seven percent. By outperforming the attorney baseline in the report, Counsel Stack excelled at identifying and citing relevant and valid primary law sources, an essential differentiator for legal AI products over generalist alternatives. "This metric matters more than raw accuracy because courts don't accept unsubstantiated legal assertions. They demand proper citation to valid, binding authority. In the past two years, over 400 attorneys have been sanctioned for citing hallucinated or invalid cases in court filings. An answer that states the law correctly but lacks authoritative primary source citations can cost a client their case or an attorney their license," Wooding said. "Our authoritativeness score versus ChatGPT's represents the difference between defensible legal work and professional liability exposure." Wooding also said Counsel Stack's built-in compliance infrastructure transforms it from a research tool into an enterprise risk management system that goes beyond "convenience features." "They're a form of malpractice mitigation. While ChatGPT Enterprise costs $200/month and provides quick research, Counsel Stack's $300/month price point includes features that generalist AI cannot provide: exportable research logs, timestamped citation verification trails, integrated timekeeping for billing compliance, and audit-ready documentation. When a judge questions a cited authority, or a bar complaint alleges inadequate research, Counsel Stack's verification logs provide a contemporaneous record proving due diligence. You're not buying slightly better citations—you're buying professional indemnification and regulatory compliance infrastructure that generalist AI will never offer." VAILS also noted Counsel Stack's consistent quality, reporting it outperformed the lawyer baseline by nine percentage points and demonstrated the ability to augment and enhance legal research capabilities for practicing attorneys. "While these attorneys outperformed AI on certain question types requiring deep contextual judgment, Counsel Stack demonstrated its greatest value as a performance floor," said Wooding. "On questions where the attorney baseline scored particularly low—complex multi-jurisdictional research, obscure regulatory questions, and comprehensive statutory analysis—Counsel Stack consistently delivered high-quality, well-cited answers. When attorneys scored 60% on complex questions, Counsel Stack scored 90%. This 30-percentage-point gap reveals Counsel Stack's role: not replacing lawyers, but preventing knowledge gaps from harming client outcomes when even excellent attorneys encounter unfamiliar terrain." Counsel Stack was also found by VAILS to be superior to generalist AI on sources by achieving significantly higher authoritativeness scores compared to generalist AI products, reflecting the value of access to proprietary legal databases and specialized training on legal sources. The VAILS results were all the more stunning, considering Counsel Stack outperformed all others in the study with a fraction of their competitors' resources. Companies participating in the study enjoyed 20-to-500 times the financial resources under which they operate compared to Wooding's company. "We outperformed well-funded competitors.. with only $200,000 in pre-seed funding, one founding attorney-engineer, and one software engineering intern. While competitors have raised millions and employ teams of dozens, we achieved the highest scores across all evaluation criteria. The performance gap at current resource levels suggests that with comparable funding and team size, Counsel Stack's lead would be substantially wider." The $200,000 pre-seed funding came from Brown and White Ventures in Q1 of 2025.