UniCourt has introduced a novel product termed UniCourt DEEP, an acronym for Docket Extraction and Enrichment Platform. This product, currently in its beta phase, integrates large language models (LLMs) with APIs to enable law firms, insurers, and legal tech companies to extract specific data points from UniCourt’s extensive collection of over one billion dockets and documents. Subsequently, this data can be delivered precisely where needed, whether to data lakes or software solutions such as Foundation.
UniCourt DEEP leverages an extensively normalized and structured database of litigation data across more than 40 states and over 3,000 state and federal courts in the US. By combining this robust database with advanced AI features, UniCourt DEEP allows users to create customized docket and document views, tailoring the extracted data points to their unique needs. Additionally, docket data extracted through DEEP can be directly integrated into popular applications, such as Litera Foundation, or pushed to data warehouses like Snowflake, Salesforce DataCloud, Azure Synapse, and Microsoft Fabric.
A key feature of DEEP is its unparalleled real-time access to court data with 100% uptime, a crucial element for use cases requiring up-to-date information. This real-time access sets a new standard in the legal tech industry. The platform enables LLM prompt engineering techniques to help users find and structure exactly what they are searching for from dockets or documents.
“Our aim is to allow the subject matter experts to leverage their knowledge in our AI tools to easily find and structure exactly what they are looking for,” said UniCourt founder and CEO Josh Blandi. This significantly simplifies the process for firms, insurance carriers, and legal tech companies to build applications and custom AI models on the data provided by UniCourt DEEP.
According to Rob Lynch, COO and former head of product at UniCourt, the product arose from recognizing that some law firms required more specific data points than the standard offerings through UniCourt’s APIs. With DEEP, customers can extract the precise data they need without a massive engineering team. It empowers them to find, extract, and push information to desired locations independently.
UniCourt provided a demonstration of DEEP, explaining how users could customize their views of court data. For instance, a user might look for all cases involving chest injuries where awards exceeded $500,000. Using structured fields like Case Type and Court, they can refine the search and extract specific details within those documents using AI prompts. This data can be further piped into other applications as needed.
The product has transitioned from a private alpha phase and is now entering a public beta stage, enabling new data integration pipelines to connect with additional platforms like Foundation and Salesforce. Although currently limited to verdict data from personal injury cases, UniCourt plans to expand the product’s capabilities and aims to launch the production version by the fall. The company will be demonstrating DEEP at ILTACON this week.
For further details, see the original article on LawNext.