Skip to main navigation Skip to content

Legal Document Management and Robotic Process Automation

Urvin Legal Use Case

Business Challenge

Urvin was approached by a Fortune 500 company whose in-house legal team was struggling with the volume of legal contracts that they had to review. They had made use of Robotic Process Automation (RPA) tools in the past, but had not found one that could meet their unique requirements and workflow. They sought a solution that would be able to:

  • Document Classification: Classify legal documents according to type (e.g., MSA vs NDA);
  • Clause Detection: Identify clauses in the contract, independent of the clause title;
  • Terms and Metadata Extraction: Extract relevant metadata (parties, contract size, important dates) and various contract terms; and
  • Be easily adopted and used by their employees, some of whom were not technologically sophisticated.

Their goals were to increase process efficiency, reduce operational risks and expose new functional capabilities for the processing and review of legal documents leveraging AI in their RPA pipeline. Ultimately, they hoped to layer on functionality to compare contract terms to their preferred terms, highlight discrepancies, and eventually to suggest red-line changes to contracts.

Urvin’s Approach

Despite competing against more established RPA and legal technology companies, Urvin brought a unique combination of expertise and resources to this solution:

  1. The ability to build custom-developed software to match the client’s exact requirements and workflow.
  2. The partnership with O3 World ensuring that user interface and experience were foundational to the solution.
  3. The ability to leverage our advanced natural language engine, and incorporate existing open source technology for a best-of-both-worlds solution.

Urvin and O3 World built this client a virtual paralegal that was easy to use, and able to integrate into their existing ticketing and workflow management systems. Besides the ability to leverage AI to more intelligently perform the necessary tasks of document classification, clause detection and terms/metadata extraction, Urvin developed a unique email-based interface. This interface ensured that employees who were not technologically sophisticated could interact with the virtual paralegal as if it were another employee. They could forward a contract to the virtual paralegal, and immediately:

  • Get an email response with some information about the contract;
  • Have tickets automatically created in the ticketing system;
  • Have individual clauses routed for review to the appropriate personnel, both on the legal and business sides of the company; and
  • Have the contract clauses compared against the company’s preferred terms, with discrepancies highlighted for review.

In addition, O3 World built a customized dashboard for tracking contract review status, progress, and overall statistics on the process, with the ability to search across and drill down into documents. For example, if the client wanted to review contracts as part of a due diligence process for a potential acquisition, those contracts could be loaded into the system, and automatically searched for all of the “Assignment” clauses to ensure there would be no problem as part of the acquisition.

The Result

Despite more established competitors, the client was impressed with Urvin’s solution. Leveraging existing systems that they were already comfortable with (email, their current ticketing system, Microsoft Word for document editing and highlighting) meant that user adoption would be straightforward and successful. Urvin was able to successfully identify an approach to the entire business challenge, rather than simply show an AI system with high accuracy, and ultimately provided a complete solution to the challenge. It was also clear that Urvin’s solution provided a clear roadmap to a future of advanced, customized functionality and increasing levels of automation.

AI Thoughts + Insights

Case Study
Product Classification for a Global Tax Software Company
Helping one of the largest e-commerce platforms in the world figure out if there was an automated, scalable way to classify the product to collect the appropriate sales tax.
Product Classification for a Global Tax Software Company
Thought
When Artificial Intelligence Fails, the Perils of Accuracy
Despite its utility, “system accuracy” is often the wrong metric to focus on and can result in very problematic behaviors and results.
When Artificial Intelligence Fails, the Perils of Accuracy
Case Study
Data Linking for a Noisy, Huge Dataset
Urvin was approached by a firm who needed to process petabytes of noisy data with a reasonable hardware footprint and processing time.
Data Linking for a Noisy, Huge Dataset