At the Legal AI and Innovation Summit hosted by Inside Practice on November 21, 2024, three leaders in the intersection of law and technology took the stage to discuss “The Future (and current) State of Search and AI’s Impacts on Knowledge Work More Broadly”. This 4-part blog series recaps their insights and predictions for how search will continue to shape the legal profession.
The panel featured Oz Benamram, Chief Knowledge and Innovation Officer at Simpson Thacher & Bartlett LLP; Yannic Kilcher, CTO and Cofounder of DeepJudge; and moderator Ilona Logvinova, Director of Practice Innovation at Cleary Gottlieb Steen & Hamilton LLP. Together, they explored the rise of contextual and interactive search, how AI-powered tools are redefining document relevance and retrieval, and how these advancements are reshaping the practice of law.
In the next part of the panel, the participants delved into the critical importance—and inherent complexity—of search. Yannic Kilcher emphasized that search, or retrieval, extends far beyond its conventional understanding. He explained that it serves as the foundational mechanism for efficiently accessing and utilizing data across a wide range of AI-driven applications.
“Search is not just the search box you type into. At its core, search means precise and fast access to data. Anything that needs access to data in a compliant, fast, and precise way—whether it’s an interface for humans to use directly or for use in other software applications—that’s a search problem,” Kilcher explained.
He elaborated that search should be viewed as a foundational capability that powers not only document retrieval but also a wide range of AI workflows, agents and tools. For instance, search enables interactive analysis, supports applications that depend on real-time data, and fuels advanced AI processes like retrieval-augmented generation (RAG). Kilcher underscored the importance of designing search systems to meet dynamic needs, making them central to how organizations access, interact with, and act upon their data.
As the panel entered its final stretch, Benamram predicted a future where search systems enable lawyers to interact dynamically with data. He described a vision of lawyers asking systems specific questions—such as identifying trends or drafting first drafts—directly from search results.
“Imagine asking, ‘What’s the average high and low for this clause when Skadden is on the other side?’ That’s where we’re headed,” Benamram said enthusiastically.
When asked how search technology will evolve, Kilcher outlined a vision of its development across three layers: retrieval, interactivity, and, ultimately, interpretation and action. The first layer focuses on retrieving existing information—whether that's a matter, a clause, or other relevant content. The second layer introduces interactivity: once you've retrieved your documents, the focus shifts to engaging with them more meaningfully.
The third layer, which is rapidly emerging, involves actively interpreting the retrieved information and taking action based on it. "Today, we always want to show people the things that exist so they can verify," Kilcher noted. "But workflows and processes built on top of search are the next step." He emphasized that now is the time "to start experimenting."
Watch the third part of the panel here:
Video will play from the 29 minute mark
Other posts in the series "The Critical Role of Search in Legal AI":
Part 1: The History and Evolution of Search in Law Firms
Part 2: Contextual Search and AI-Driven Innovations
