Technology Assisted Review

A lawsuit has been filed. Both parties have met and negotiated an ESI Protocol that has been formalized as a court order. Your review team has started the initial review and notices there are numerous duplicates. When this is brought to your attention, you discuss with your litigation support team and they suggest de-duplication and email threading as options. Which of the following would steps would be appropriate? In this blog, we'll dive into the next steps in this scenario and the importance of having an ESI Protocol in place.

Two recent decisions highlight the usefulness of phased e-discovery as a tool to satisfy Rule 26(b)(1)’s ever-important proportionality requirement. Model orders for patent cases in numerous courts require phased discovery, typically phasing email discovery to occur after other discovery and only if deemed necessary. However, phased discovery is becoming prevalent in other types of cases as well.

Last fall, I had the pleasure of speaking on a panel at the 2019 Relativity Fest entitled “Why Lawyers SHOULD Be Luddites.” It was a lively discussion about whether lawyers should be luddites, whether robots would be taking attorney jobs, should attorneys learn to code, and how to future-proof yourself. Opinions were split but what struck me the most was that a majority - if not all – of the attendees wanted to learn how to future-proof themselves. In this blog I offer tips on how to take advantage of technologies to do just that.

Last year, in In re Broiler Chicken Antitrust Litigation, the United States District Court for the Northern District of Illinois laid out a very detailed protocol for conducting TAR that can serve as a go-by for parties wishing to conduct TAR in their own litigation. If you are considering implementing TAR in your next review, you may want to take a look at this. 

Recently, I began work on a complex litigation case that had millions of documents to review with many moving parts and quick deadlines that made completing assignments daunting, to say the least. We determined that simply running targeted searches to find this evidence was not the best approach, in part because the issues were broadly defined and had multiple subparts, and in part because of the sheer number of documents in the database (over 2.5 million records). As an alternative, we decided to utilize technology assisted review or “TAR” (also known in the industry as predictive coding). What follows is my impression of the tool.