AI/Watson

AI speeds document discovery, giving law firms a leg up

Share this post:

Here’s some food for thought on where technology fits into the legal profession. First, ask a hundred lawyers why they chose their calling. Then ask 100 clients how they want their law firms spending their time and racking up billable hours. The chances are that neither group mentioned the time-consuming drudgery of the early discovery, one of the very first processes of civil litigation.

In a nutshell, early discovery is what law firms do when their client first receives a complaint. Usually performed by either paralegals or junior associates, it involves sifting through the complaint for information needed to create an early-phase response draft, all of which needs to happen in relatively short order. Because the document analysis has traditionally been such a high-touch, labor intensive process, the costs associated with the discovery phase—part of all the back and forth between attorneys required just to get to trial—can often exceed the cost of the trial itself. As such, it can serve as a kind of barrier to ever bringing a lawsuit, even a strong one.

Lawyers and clients push for change

Two powerful and converging forces have made the discovery process ground zero for technology-based innovation in law firms today. One comes from clients who see technology as a way to reduce their legal costs and speed up the process. The other comes from lawyers themselves, who see technology as a way to free them up to focus on the finer points of litigation strategy—like interviewing, investigations, legal research and writing the most polished briefs—in short, the tasks that make them happy to be a lawyer.

Thomas Suh and I founded LegalMation because we saw the rapid maturation of AI as having the potential to disrupt the high-volume, low-value layer of work in the legal industry by automating and accelerating it. We recognized that to realize this potential, we needed AI technology that was not only powerful, but also easy and intuitive from an end-user standpoint. Those are just the qualities we found when we started working with IBM.

Legal SMEs encounter AI

After first exploring the capabilities of IBM’s AI using an IBM Watson Discovery sandbox environment, we put together a team of legal subject matter experts (SMEs) to use IBM Watson Knowledge Studio and IBM Watson Natural Language Understanding running on IBM Cloud to create a domain-specific model focused on legal terminology and concepts.

To train the model, our team fed thousands of lawsuit complaints and responses into it, with a specific focus on entities and relationships that are critical to formulating new early-phase documentation. At that stage of development, we defined success as the degree to which Watson could accurately capture the nuanced distinctions within legal text that trained attorneys make.

We had high expectations going into the project, but nothing prepared us for just how well Watson was able to make those distinctions almost from the very start.

Users of the complaint analyzer module—attorneys or paralegals—upload the civil complaint document and, after 3 clicks and approximately two minutes, downloads first drafts of written discovery (such as requests for production and interrogatories) and an answer.

Interested in streamlining document analysis?

Beyond costs savings

It would be tempting to point to the huge reduction in the length of the early discovery—from roughly 8 or 10 hours to two minutes—as the marquee benefit of our AI solution. But we see its true payoff for law firms on a strategic level. For one, it enables law firms to keep their lawyers focused on the activities that matter most, exercising the skills that are pivotal in winning cases and stoking pride and satisfaction in their work. That’s how you keep the best, most talented attorneys who are the bedrock of a firm’s future.

Second, our solution makes it possible for law firms to offer more competitive alternative fee structures. Whereas the traditional model can’t help but build in the high and often unpredictable costs of the discovery process, our solution all but eliminates it, focusing instead on outcomes. That’s especially critical in civil cases that might previously have been considered not worth pursuing due to the high pre-trial costs. What we’re offering is the potential to transform the business model for law firms.

Watch James Lee talk about how AI can transform the way law firms work and compete:

Co-Founder and CEO

More AI/Watson stories

Hit by a hurricane? InsurBot can help with your claim

Call centers at insurance companies face enormous pressure when natural disasters strike. Policyholders hurting from their losses need urgent help. But customer service agents can be overwhelmed by the spike in calls. That happened in recent years when a record number of hurricanes, floods and other disasters hit the United States. Policyholders were turned off […]

Continue reading

CIMON, the AI-powered robot, launches a new era in space travel

Outer space is unfriendly to humans. We can only exist in a contained environment with its own air supply, so that means working in very close quarters. Zero gravity means things don’t stay where you put them. Despite these constraints, astronauts on the International Space Station (ISS) must be highly productive on a very tight […]

Continue reading

AI insights from Behr help consumers pick their paint palette

Behr Paint Company offers more than 3,000 colors in our paint collection. We find that consumers often get confused when it comes to picking the right color for their project. They’re overwhelmed with choice, causing a kind of analysis paralysis. Often, people don’t take on or complete a painting project because of their struggle to […]

Continue reading