On this episode of The Geek in Review, hosts Marlene Gebauer and Greg Lambert explore innovations in legal search with Paulina Grnarova and Yannic Kilcher, co-founders of DeepJudge. This semantic search engine for legal documents leverages proprietary AI developed by experts with backgrounds from Google and academic AI research.

As PhDs from ETH Zurich, Grnarova and Kilcher recognized lawyers needed better access to institutional knowledge rather than constantly reinventing the wheel. DeepJudge moves beyond traditional keyword searches to a deeper integration of search and generative AI models like GPT-3. Partnerships provide financial support and key insights – advisors include execs from Recommind and Kira Systems while collaborations with law firms shape real-world product capabilities.

Discussing product development, Kilcher explains connecting search to language models allows generating summaries grounded in internal data without ethical or security risks of training individual models. Grnarova finds the core problem of connecting users to full knowledge translates universally across firms, though notes larger US firms devote more resources to knowledge management and data science teams.

When asked about the future of AI, Grnarova expresses excitement for AI and humans enhancing each other rather than replacing human roles. Kilcher predicts continued growth in model scale and capability, requiring innovations to sustain rapid progress. They aim to leverage academic research and industry experience to build AI that augments, not displaces, professionals.

DeepJudge stands out for its co-founder expertise and proprietary AI enabling semantic search to tap into institutional knowledge. Instead of reinventing the wheel, lawyers can find relevant precedents and background facts at their fingertips. As Kilcher states, competitive advantage lies in accumulated know-how – their technology surfaces this asset. The future of DeepJudge lies in combining search and generative models for greater insights.

Listen on mobile platforms:  ⁠Apple Podcasts⁠ |  ⁠Spotify⁠ | YouTube (NEW!)

Links:

Contact DeepJudge: info@deepjudge.ai⁠

Contact Us: 

Twitter: ⁠⁠⁠⁠⁠@gebauerm⁠⁠⁠⁠⁠, or ⁠⁠⁠⁠⁠@glambert⁠⁠⁠⁠⁠

Threads: @glambertpod or @gebauerm66

Email: geekinreviewpodcast@gmail.com

Music: ⁠⁠⁠⁠⁠Jerry David DeCicca⁠⁠⁠⁠

Transcript

Continue Reading Paulina Grnarova and Yannic Kilcher from DeepJudge.AI: Unlocking Institutional Knowledge: How AI is Transforming Legal Search (TGIR Ep. 224)

This episode of The Geek in Review podcast provides an in-depth look at how the AI assistant Paxton, created by Tanguy Chau and Mike Ulin, is transforming legal work. The hosts speak with the founders of Paxton to explore the pain points their technology aims to solve and how generative AI can enhance lawyers’ capabilities.

Tanguy and Mike discuss their backgrounds in AI, regulatory compliance, venture capital, and management consulting. This diverse experience informed their vision for Paxton as an AI assistant specifically built for legal and compliance professionals. They explain that Paxton is trained on millions of legal documents and regulations, allowing it to search this vast knowledge and retrieve highly relevant information rapidly. A key feature they highlight is Paxton’s accuracy in citing sources, with every sentence linked back to the original text.

One of the key features of Paxton is that it can automate repetitive, low-value legal work to make lawyers more efficient. Tanguy notes that tasks like reviewing thousands of sales contracts clause-by-clause or compiling 50-state surveys that once took weeks can now be done by Paxton in minutes. Mike discusses Paxton’s advanced document comparison capabilities that go beyond keyword matching to understand meaning and intent. This allows quick, substantive analysis of contracts, marketing materials, and more.

Exploring the future, Mike predicts that like software developers, lawyers who embrace AI will become much more productive. But higher-level strategic thinking will remain uniquely human. Tanguy shares an analogy of a human on a bicycle outpacing a condor, the most efficient animal. He believes combining human creativity with AI tools like Paxton will enable radically new levels of efficiency and capability.

Paxton.AI’s Tanguy and Mike make a compelling case that AI-powered tools such as Paxton will fundamentally transform legal work. By automating repetitive tasks, AI will free lawyers to focus on high-value, client-facing work. Overall, this episode provides great insights into how generative AI may soon become indispensable for legal professionals seeking to improve their productivity and capabilities.

As a special treat, we wrap up the interview with a demonstration of Paxton.AI’s capabilities. (YouTube only)

Links:

Paxton AI (try the Beta for free)

Forbes Article: Unlocking The 10x Lawyer: How Generative AI Can Transform The Legal Landscape

Using Generative AI to analyze the 45 page Trump Indictment using Paxton AI

Unveiling Paxton AI’s Newest Features: Boolean Composer and Document Compare

Instantly Analyzing the Congressional UFO Hearing with Generative AI powered by Paxton AI

Transcript:Continue Reading Paxton.AI’s Tanguy Chau & Michael Ulin: How AI Allows Legal Work to Soar to New Heights (TGIR Ep. 220)

It is pretty apparent that we are in a super Hype Cycle when it comes to AI tools like ChatGPT, but for many of us in the legal profession, we’re not used to reaching this point of the cycle at the same time as the rest of the world. Because things are happening so fast, we wanted to bring in someone like Colin Lachance from Jurisage to talk about how they are integrating Generative AI tools into their products.
Greg was going down an AI rabbit hole on Twitter this week when Colin mentioned his own project he was launching. Jurisage’s tool, MyJr (pronounced “My Junior”) is part of a joint venture between Jurisage and AltaML, and is designed to change how researchers access information by allowing the AI tool to synthesis and read cases as the researchers search and analyze the information. Rather than opening up web browser tab after tab and scanning cited cases for relevant information, the idea behind MyJr is to have it quickly answer that information for you. If you need to know what the relevant arguments are from each side in Smith v. Jones, as MyJr to pass that along to you. Ask it a plain language question, get a quick and plain language answer.
Lachance is working to use the GPT 3.5 tool to pass along cases and create what he calls “guardrails” with the cases so that the prompt and the results limit themselves to the case itself. This protects the researcher from the AI “creating” the answer from all the non-relevant information it has collected in its large language model of machine learning. Lachance has additional goals for using AI within Jurisage’s data, but he’s focused tools like MyJr establishing trust with those using it for researching Canadian, and soon US caselaw.
The MyJr product works as a browser extension and identifies Canadian and US case law citations on any web page. It delivers a preview into key details about the cited case, and a link to a free full-text version, in a popup when the user hovers over the citation. Clicking through to a “more insights” dashboard reveals additional detail as well as access to the upcoming “Chat with a case” feature (Feb 20th for Canadian case, a month later for US). While the paid version of the dashboard won’t officially launch until late March, user can get unlimited pre-sale access today as well as secure a future 50% discount option for a one-time payment of $7.

Listen on mobile platforms:  Apple Podcasts LogoApple Podcasts |  Spotify LogoSpotify
More information on Jurisage and MyJr can be found here:
Contact Us:
Twitter: @gebauerm, or @glambert
Voicemail: 713-487-7821
Email: geekinreviewpodcast@gmail.com
Music: 
Jerry David DeCicca
Transcript

Continue Reading Colin Lachance on Jurisage’s MyJr and How He’s Looking at AI to Assist in the Synthesis and Reading of Legal Cases (TGIR Ep. 190)

This week we have Debbie Reynolds, “The Data Diva,” join us to discuss the current state of data regulations, privacy, access, and what’s on the horizon for data in the legal industry. Debbie is a 2022 ABA Women in Legal Tech Honoree and the host of The Data Diva Talks Privacy Podcast.
According to Debbie, there is exponential growth going on in technology and the types of data that is being captured. At the same time, governments across the globe are trying to find ways of regulating how businesses and organizations can capture and use data they gather from individuals. These two event are not coordinated so it has created a “Wild West” situation where the law is trying to catch up to the realities of data gathering in the business world.
Training on data security is also lagging behind what is really needed today. Most training on data security is framed around the idea that “data security is everyone’s responsibility.” Reynold’s response to that is unless you are more specific about what it is you need people to do in regards to data security, then it turns out that “everyone’s responsibility is actually no one’s responsibility.”
As technology advances beyond encryption, satellite integration, IoT devices, and morphs into the Metaverse, the types of data produced and gathered is going to completely overwhelm any government’s ability to regulate it. The Data Diva thinks that if we don’t start creating more transparency when it comes to individual’s data privacy, it’s just going to get more and more complicated than it is right now.

Listen on mobile platforms:  Apple Podcasts LogoApple Podcasts |  Spotify LogoSpotify
AALL Crystal Ball Answer
Wolters Kluwer’s Anand Daga is our last AALL Crystal Ball response. His view of how the legal information industry will change in the next two to five years revolves around how the information is delivered to the end users. He sees things in much smaller chunks of information delivered to the researchers in shorter, practical methods in ways that value the practitioner’s time.
At Legal Value Network eXperience

Greg is going to LVNx this week and will have The Geek in Review stickers to hand out. So if you’re in Chicago at LVNx, be on the lookout and prepared to answer our Crystal Ball Question!

Contact Us:
Twitter: @gebauerm or @glambert
Voicemail: 713-487-7821‬
Email: geekinreviewpodcast@gmail.com
Music: 
Jerry David DeCicca
Transcript

Continue Reading The Data Diva and Two Geeks Talk Data Privacy – Debbie Reynolds (TGIR Ep. 174)

When it comes to dockets, the holy grail for most of us has always been state trial court dockets. Nicole Clark, CEO and co-founder of Trellis also felt that way when she was practicing, and decided that she would find a way to access and obtain that treasure trove of data that was always just out of reach. Nicole sits down with us this week to tell us the story behind her mission to seek out local court information, clean up the data, and create a method of analyzing that data. As anyone who has ever worked with trial court dockets, you understand how difficult a task this really is.

Nicole says that Trellis is on a mission to add a county court a day and to find additional ways that the information can be sliced, diced, and analyzed with the help of artificial intelligence (AI) processes like natural language processing (NLP) and through upcoming API access. She also walks us through some of the unique ways her customers use the data, and that the value of trial court data isn’t just limited to the legal field. The once elusive state court data is now becoming more and more available through platforms like Trellis, so the opportunities for legal researchers to take advantage of this wealth of information is expanding, literally by the day.

In a first, Nicole and Trellis is offering a free trial for TGIR listeners:

Listener PerkTrellis is providing Geek In Review podcast listeners with complimentary 14-day access to its state trial court research & analytics platform!  Gain insights and intelligence on judges, verdicts, opposing counsel, motions, rulings, dockets and other legal issues.  Click here to try Trellis for free today.

LegalWeek Crystal Ball Question

This week we ask Casetext’s Robert Armbruster to look into his crystal ball and tell us what he sees in the next few years when it comes to our expectations on how search tools like Casetext will evolve.

Listen on mobile platforms:  Apple Podcasts LogoApple Podcasts |  Spotify LogoSpotify

Contact Us
Twitter: @gebauerm or @glambert
Voicemail: 713-487-7270
Email: geekinreviewpodcast@gmail.com
Transcript

Continue Reading The Geek in Review Ep. 156 – Nicole Clark on Trellis and State Trial Court Docket Analytics

There were a number of SNAFUs the past couple of weeks here at The Geek in Review, but even with scheduling difficulties and personal emergencies, we wanted to get an episode out this week. In order for everyone to “get their geek on,” we created an “Information Inspirations” episode. We’ll be back next week with more traditional content, but we hope you enjoy our musings on news and ideas around the legal industry.

Listen on mobile platforms:  Apple Podcasts LogoApple Podcasts |  Spotify LogoSpotify
Information Inspirations
Bill Henderson’s State supreme courts and the challenges of PeopleLaw discusses the power that state supreme courts have in the regulation and delivery of the legal industry and access to justice. These courts have the power over the market structure, dispute resolution, and licensure of the practice of law. However, the Justices are reluctant regulators and Henderson suggests that they need to shake off this reluctance and fix a system that is in serious need of change.
The American Bar Association is poised to change a series of law school accreditation rules and the change could go into effect as early as this fall. This round of changes deals with anti-discrimination training that law students need to take before they can graduate. 
The ROSS v. Westlaw battle continues with ROSS recently crying foul that Westlaw is using copyright arguments to maintain what they claim to be a monopoly on legal information. Julie Sobowale dives a little deeper on one issue that affects both US and Canadian legal research innovators, and that is access to primary materials like case law. 
Law School 1Ls and 2Ls shouldn’t just look at BigLaw for their summer associate work. Working with startups or venture capital firms may be another option out there. 
The legal industry looked to the NFL’s Rooney Rule to help guide our own version through the Mansfield Rule. While the NFL gave a good blueprint for how to expand the search for minority talent, a recent lawsuit by former Miami Dolphin Head Coach, Brian Flores, alleges that it is also a blueprint for how to claim we are doing great things for minority hiring, but the reality is that it is a check-the-box and continue-as-normal process.
The era of COVID produced a major shift in the concepts of virtual court proceedings. While we’ve had bumps in the road, it seems that virtual courts are here to stay. 
Bonus Inspirations
Contact Us
Twitter: @gebauerm or @glambert.
Voicemail: 713-487-7270
Email: geekinreviewpodcast@gmail.com.
Transcript

Continue Reading The Geek in Review Ep. 146 – All Information… All Inspirations

It’s the episode of The Geek In Review that Greg has dreamed about. Beer law!

Courtney Selby, Associate Dean for Information Services, Director of the Law Library, and Professor of Law at Hoftra University Law School, walks us through the strange and interesting topic of beer laws. Selby has immersed herself in the topic for years, and has an upcoming publication with W.S. Hein on Brewery Law with a national survey of state laws on the topic. Not only does Courtney Selby explain some of the more bizarre rules around beer, ciders, and other alcohol laws, she also give some great suggestions on different beers to try.

Apple Podcasts LogoApple PodcastsOvercast LogoOvercastSpotify LogoSpotify

The Geek In Review is now available on Spotify and Stitcher platforms. That brings us up to over a dozen platforms. So make sure that you subscribe on whatever your favorite platform is. Chances are, we’re there.

Information Inspirations:

Rob Saccone’s article, Fractal dysfunction and the mathematics of #biglaw innovationdiscusses moving your innovation ideas off of the drawing board and into measurable actions. Saccone brings out his inner-math nerd to walk us through the fractals and the vectors of making innovation more than just an abstract concept. Shout out to Jae Um for her inspiration on this article.
Continue Reading Courtney Selby on Beer Law