Litigators can start using artificial intelligence for research with online tools such as CARA, EVA, and IRIS. This post compares these three research tools, describing their benefits and limitations, and explains how they might be able to save you time in your litigation practice.
Our Verdict: while each of these applications has the potential to save litigators valuable hours researching a case, none of these services fully deliver as advertised. Below we give a summary of each AI research tool, including their benefits and limitations.
CARA is an AI powered technology that is supposed to help legal researchers find the best cases in a faster manner, including cases that might go overlooked.
You can use the CARA search by entering traditional search terms and connectors in its search bar or you can upload a legal document, such as a brief or complaint, which CARA will then search and analyze in order to find the most relevant results related to the document. You can tailor your results by entering new keywords and filters.
Bottom line: CARA will save you time if you need to quickly access and generate a list of the cases cited in a brief. CARA can possibly find cases you may have overlooked. CARA, like us humans, is not perfect and has some way to go before you can completely rely on this AI to find all of the cases you should be citing in your legal documents.
- Analyzes various legal documents, such as briefs and complaints. It is not limited to briefs alone.
- Free for all individuals to access the law (meaning cases). Current law school students, faculty, staff, members of the judiciary, and their clerks can request complimentary access to Casetext’s premium features.
- Lists (most of) the cases cited in an uploaded brief or legal document, with links to the cases.
- Suggests cases that relate to the facts presented in your uploaded document.
- Secure. Casetext does not save any documents uploaded to CARA.
- If you place your cursor in the search box, a helpful explanation will appear regarding Boolean connectors so that you can better enter search terms.
- Only identified 14 of the 15 cases cited in the brief we uploaded.
- Did not identify any of the statutes cited in the brief we uploaded.
- Once we entered a term into the “filter and narrow” search bar, we could not delete the term unless we replaced it with a different term.
- While negative treatment of cases is noted, there is no way to determine if the holding is negative regarding the issue you are arguing unless you read the case yourself.
Individuals can access premium features for $139 a month. Law firms must request a quote for a custom monthly subscription costs.
EVA is an AI research tool developed by ROSS. Users can upload a brief into EVA to analyze whether or not the cases cited in the brief have any negative treatment. EVA also provides links to all of the cases cited in the brief once a brief has been processed.
Bottom Line: EVA is visually appealing, and like CARA, will quickly link you to cases cited in a brief for quick and easy searching. The best feature is the ability to highlight text in a brief to find cases on point with the argument you or opposing counsel is trying to make. The NLP tech is impressive.
- Free for all users.
- Provides links to cases within the brief you uploaded.
- Will list cases with negative treatment.
- You can highlight sentences in the uploaded brief to find similar language used in other cases.
- Easy to read format.
- Secure. EVA does not save any of the uploaded briefs.
- Allows for Natural Language Processing (NLP) search in cases, simplifying the process for finding a case holding/main issues
- Only analyzes briefs.
- Does not make case suggestions to include in your brief.
- Only identified 14 of the 15 cases cited in the uploaded brief.
- You cannot search regulations, statutes, procedural law, or secondary sources.
IRIS is an AI research tool that helps users explore scientific papers and TED talks. Its search tool generates a visual representation of how your chosen paper connects to other scientific studies available on the internet based on keywords.
When we first learned of this tool, we were hoping that it could be used for researching science based topics that are frequently litigated in the courtroom (such as Daubert motions). To test IRIS, we uploaded a link to a paper on retrograde extrapolation of blood alcohol concentration levels hoping that IRIS would link us to other papers related to the topic. Instead, IRIS linked to what seemed like every paper not related to retrograde extrapolation, including research on black holes. Obviously, the tool still requires development before you can use it to effectively research technical topics.
Bottom Line: IRIS is a great concept and visually appealing, but it’s not ready to help with your litigation research.
- Visually appealing.
- Breaks complex concepts into key words.
- Must link to a scientific research paper that follows a specific format or a TED talk for the search to work.
- Scientific papers linked to key words are often unrelated to the first scientific paper uploaded.
Are you aware of any other AI powered research tools? Please let us know in the comments.
About Trial by Tech
Trial by Tech is a blog brought to you by Baylor Law’s Executive LL.M. in Litigation Management—the first program in the nation designed exclusively for lawyers who aspire to direct effective litigation strategy, control electronic discovery, leverage technology, manage a team, and lead their company’s or firm’s efforts to manage a high-volume, high-stakes docket.
Here, you will find focused discussions on the #innovation of litigation and the intersection of #legaltech and #litigation. If you like what you are reading, many of the posts are authored by experts from the LL.M. program. To learn more, click here.
Attorneypreneur, writer, technologist. Nerdy for legaltech, politics, crypto, cybersecurity, innovation. Presently in-house at Williams & Brown. Former adviser at Baylor Law, and founder of two technology and legal consulting companies. @JoshuaWeaverEsq