Sherlock AI
Smart, machine-learning algorithms that make finding
documents faster and easier than using keywords alone.
Meet Sherlock
Sherlock is our AI-powered digital document bloodhound. He runs on a set of smart, machine-learning algorithms designed to make it easier to find information in large document populations.
Sherlock eliminates the need to craft complicated keyword searches. Instead, send one or more documents to Sherlock and let him find more. In milliseconds, Sherlock will analyze the documents you’ve sent, build an AI model, apply it to the larger document population, analyze and rank them for relevance and then present the next likely relevant documents for your review.
Sherlock’s strength is his speed, scalability and flexibility. He can analyze and rank a million documents in 100 milliseconds, 10 million in a second. Sherlock will then deliver new documents in order of likely relevance, allowing you to review and mark them relevant (“Thumbs Up”) or not (“Thumbs Down”).
Send one document to Sherlock or send hundreds. Sherlock will analyze them, extract key terms, build an AI model and apply the model to the other documents on the site. Once you see Sherlock in action, you won’t want to go back to using keywords alone again.
Let’s take a look and see Sherlock in action. We will walk through a simple exercise that starts with one relevant document and quickly leads to others.
Here is a quick introduction to Sherlock,
our AI-powered digital document bloodhound.
Protecting the Manatees: Starting our Search
Our assignment is to find documents regarding protecting manatees. We are searching over 2.7 million documents, many of which are emails from Jeb Bush’s two terms as governor. The possibility of manatees becoming extinct was an important issue during Jeb Bush’s term just as it is today.
Our simple keyword search for “manatee or manatees finds over 157,000 documents, many of which are about Manatee County rather than the animal we are trying to protect. This is our “snippet view” which extracts snippets of text from each returned document. It can be handy to get an idea of what kind of documents our search is returning.
While the first documents seem to be about Manatee County, we can scroll down through our snippets view to find a relevant document.
Finding a Good Document
After scrolling through a few documents about Manatee County, we find this document which is right on point.
Rather than continue reviewing the results of our keyword search, let’s send the document to Sherlock and let him find more. Just click “Send to Sherlock” and you will start finding more relevant documents.
Naming Your Session
Sherlock asks us to name our session. While this isn’t required, if you name the session, your or others on the team can come back to it, adding more documents to the session. You can also tell Sherlock to copy positive documents to a designated folder. This will save you the effort of copying them individually.
We will call this the Sherlock Manatee Investigation.
The next step is to click “Submit.” In milliseconds Sherlock will analyze the document you sent, build a machine learning model around the key terms it finds, apply that model to each of the 2.7 million documents on the site, rank each for relevance and bring back the top document along with key terms for your review.
Sherlock Brings Back a Relevant Document
Here is the first document from Sherlock. As you can see, it is right on target, focusing on the threat to Florida’s manatees. Notice that Sherlock has already identified other key terms not included with your search.
This is an important part of what makes Sherlock unique. Start with a few keywords. Sherlock will quickly find others and highlight them for you.
Let’s give our first document a thumbs up. Sherlock will bring back another document in milliseconds.
Sherlock Brings Back Another Relevant Document
This next document is also on target. The writer is worried that manatees are being killed in record numbers.
Key Terms
As we noted earlier, Sherlock will highlight key terms (often not part of your initial search) that you may find important. We offer two ways to view them. Just click on the Key Terms link at the top right.
You can view key terms in a Word Cloud. The more important terms are larger in size.
Or view the top key terms in list format. They too are ranked in order of importance.
You can boost key terms to let Sherlock know you deem them particularly important. Or choose to suppress terms that Sherlock should downplay. Either way, Sherlock will take your signals into account the next time you send a document judgment. Think of it like waiving a hankie under your digital bloodhound’s nose.
Continuing on the Trail
Here is the next document from Sherlock. We are still on the right track.
As we add each new judgment, Sherlock gets smarter and smarter about what we seek. That is the power of machine learning.
More Good Documents
And here is another good document.
Sherlock keeps finding great documents to further our investigation.
Finishing the Session
When you are done, choose an exit option to return to where you started. From there, you can continue with your keyword search or start fresh with a new search.
At any time, you can return to the session you created by sending Sherlock another document. It’s as simple as that.
Back to Keyword Search
When you finish the session, Sherlock brings you right back to your keyword search. From here you can continue reviewing documents from your search or try a new search to find other documents. Either way you can jump back into your Sherlock session at any time. Others can join in as well.
As you continue the investigation, Sherlock gets better and better at finding good documents. It is as easy as that to find relevant information in large document sets.
Sherlock in Action
Want to see more examples of Sherlock in action? Here are two more of his most important cases.
As we mentioned earlier, Sherlock can start with one or hundreds of training documents. Watch fast he creates a new AI model and analyzes just under two million documents in this short video.
During Governor Bush’s term as governor, the Florida Legislature considered a bill to allow venue’s to resell tickets. Watch as Sherlock quickly finds relevant documents in about ticket scalping.
Why Sherlock?
What makes Sherlock revolutionary is his blinding speed. Many existing TAR (technology assisted review) engines require hours to analyze and rank a million documents. Sherlock can do the job in 100 milliseconds, the blink of an eye. And there are no practical scaling limits. Indeed, Sherlock can rank ten million documents in a second or two.
We believe Sherlock’s speed and scalability will change document search, much like how Pandora changed the way we find new music. It allows users to find relevant documents quickly and easily, without having to master complex keyword search syntax. Its utility goes beyond legal, reaching to healthcare, corporate investigations, FOIA requests and other searches involving large document populations.
"What amazing magic is this? It’s almost spooky."
Welcome to Search 2.0
Contact us to find out how you can move up to Search 2.0 as well.
