This week, we sit down with Sam Flynn, COO and co-founder of Josef, to separate substance from hype in the rapidly evolving world of legal tech. Sam shares his passionate stance that “RAG is not dead,” defending Retrieval-Augmented Generation (RAG) as a foundational and still deeply relevant method for deploying AI in the legal industry—despite the flashy allure of agentic AI. His nuanced take reminds listeners that success in this space depends not only on the sophistication of the technology, but on doing the “boring” foundational work: ensuring data integrity, context-aware chunking, and responsible workflows.

Throughout the discussion, Sam champions the idea that great legal technology should not just enhance expert workflows but make legal information accessible to non-experts. With examples from Josef’s clients like L’Oréal, Bumble, and Bupa, Sam illustrates how Josef’s tools allow legal departments to offload routine work through reliable self-service systems—freeing up time for more strategic thinking while improving speed, compliance, and consistency across organizations. He makes the case that empowering end users with trustworthy tools isn’t just good tech—it’s a new model for scaling legal and compliance services.

A key highlight is Josef’s Roxanne project, developed in collaboration with Housing Court Answers and NYU. Roxanne is an AI-powered tool designed to help tenants in New York navigate the complexities of housing law. Sam outlines the safeguards that ensure Roxanne’s answers are accurate and compliant, such as closed-domain data sources, human-in-the-loop validation, and smart escalation workflows. The conversation touches on the broader access to justice (A2J) implications of this technology—arguing that when designed carefully, AI can amplify the reach and impact of legal aid organizations by orders of magnitude.

The episode doesn’t shy away from the tensions legal professionals feel when automation enters their domain. Sam offers a powerful reframing: instead of seeing these tools as a threat, lawyers should view them as opportunities to offload low-value tasks and expand their influence. The goal, he says, is not to cut jobs—but to redefine the kind of work legal professionals do, making space for more proactive, strategic, and meaningful engagements within organizations and communities.

As the conversation wraps, Sam shares his optimism about the future—tempered by a clear-eyed understanding of the human factors that will determine success. While the technology is ready, the question is whether legal professionals will step up and take the lead. His call to action is clear: focus less on the hype, and more on the systems, safety, and trust that make tech transformative. Whether you’re a legal technologist, innovator, or cautious observer, this episode offers a grounded and inspiring look at what it takes to build legal tech that actually works.

Listen on mobile platforms:  ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Apple Podcasts⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ |  ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Spotify⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ | ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠YouTube⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠

[Special Thanks to Legal Technology Hub for their sponsoring this episode.]

\

Blue Sky: ⁠@geeklawblog.com⁠ ⁠@marlgeb⁠
⁠⁠⁠⁠⁠Email: geekinreviewpodcast@gmail.com
Music: ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Jerry David DeCicca⁠⁠⁠⁠⁠⁠⁠⁠⁠

Transcript

Continue Reading RAG is Not Dead: Josef’s Sam Flynn on Legal Tech That Works

This week we welcome Chan Hee-Koh, CEO and co-founder, and Justin Brownstone, Strategic Partnership Lead at FileRead. As legal professionals and tech enthusiasts gear up for LegalWeek, the conversation starts with some lighthearted banter about the best places to visit in New York—including a passionate endorsement of Angelina in Paris’ hot chocolate. However, the discussion quickly turns toward the evolving role of AI in the legal industry and how FileRead is shaping the future of litigation technology.

Chan shares the deeply personal story that inspired FileRead’s creation: his immigrant family’s experience during the 2008 housing crisis. Seeing how legal services were out of reach for many due to the complexity and cost of litigation, he set out to develop a platform that could make legal discovery and fact-finding more accessible and efficient. FileRead focuses on litigation-specific AI applications, aiming to streamline document review, build stronger factual narratives, and uncover hidden stories within vast amounts of case data. The discussion also touches on the industry’s skepticism toward AI and the need for legal tech companies to build trust and demonstrate real value.

The conversation then turns to FileRead’s recent growth and roadmap for 2025. Having secured a $6 million seed funding round and a strategic partnership with Simplify, the company is expanding its capabilities beyond Relativity to offer a standalone AI-powered litigation analysis platform. Justin highlights how FileRead’s technology goes beyond standard eDiscovery tools by enabling instant document analysis, chronology building, and memo drafting—tasks that traditionally take weeks of manual work. The team is also working on developing litigation workflows that will automate complex fact-checking processes, helping lawyers assess case strengths and identify missing evidence more efficiently.

A key theme of the episode is the legal industry’s slow but inevitable adoption of AI. Chan and Justin discuss how legal workflows are fundamentally different from those in other industries due to the uncertainty and unpredictability of litigation. Unlike transactional law, where contracts and compliance processes are more standardized, litigation involves a constantly shifting landscape where new evidence and legal arguments can completely change the direction of a case. The hosts and guests explore how AI is beginning to bridge the gap between human expertise and technological efficiency, making legal work more strategic and less burdened by repetitive document review.

As the episode wraps up, the hosts reflect on the rapid evolution of legal technology. Greg and Marlene note that while AI has been discussed in legal tech for years, the capabilities of large language models (LLMs) have dramatically accelerated in just the last two years. Chan and Justin acknowledge that staying ahead in this fast-moving space requires constant experimentation and adaptation. However, they emphasize that while technology can enhance legal work, people remain at the center of the industry. AI should be seen as a tool that empowers attorneys rather than replaces them. To learn more about FileRead, visit FileRead.com, or reach out directly to Chan and Justin via email.

Listen on mobile platforms:  ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Apple Podcasts⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ |  ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Spotify⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ | ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠YouTube⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠

Blue Sky: ⁠@geeklawblog.com⁠ ⁠@marlgeb⁠
⁠⁠⁠⁠⁠Email: geekinreviewpodcast@gmail.com
Music: ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Jerry David DeCicca⁠⁠⁠⁠⁠⁠⁠⁠⁠

Transcript

Continue Reading Exploring AI-Powered Litigation with FileRead’s Chan Koh and Justin Brownstone

I’ve had a few conversations around the topic of Microsoft’s CoPilot and the usage and value that it will/might/could bring to our day-to-day work in the legal industry. To say that people had strong opinions would be an understatement. I found people who thought it brings great efficiency to the daily routines of lawyers and

It is probably just an odd coincidence that the two top things that caught my eye were legal innovations out of Arizona, the same week when I am going to Arizona for a weekend getaway with my lovely wife. But is seems that the weather is not the only hot thing happening in The Grand

This week featured a “Proud Parent” moment for myself as I watched my son, Dean, go to his first legal technology conference in Chicago. Dean was a Relativity Scholar this year and has been working on learning the ropes in e-discovery for the past few months. It is exciting to watch as a new generation

It’s Friday the 13th, so hopefully everyone left cookies and milk out for Jason Vorhees last night to keep him happy.

This week saw a few “launches” of new and updated products, primarily dealing with integrating AI agents into their products. OpenAI learned how many r’s there are in strawberry, vLex turned Vincent AI into

As many of us come off the high of hanging out and talking AI at ILTA, there seems to be a push this week in the articles for AI tools to “show me what you’ve done for me lately?” This makes sense that once you get back to the office and need to show existing