We and selected third parties use cookies or similar technologies for technical purposes and, with your consent, for other purposes as specified in the cookie policy. Denying consent may make related features unavailable.
You can consent to the use of such technologies by using the “Accept” button, by closing this notice, by scrolling this page, by interacting with any link or button outside of this notice or by continuing to browse otherwise.
No items found.

New AI patent awarded to Roots Automation

Julianna Rice
August 26, 2022

Novel Human-in-the-Loop AI technology enables Digital Coworkers to interact with humans in real-time to manage exceptions and complete business processes end-to-end.

NEW YORK, July 28 2022 – The U.S Patent Office has awarded Roots Automation a new patent based on their unique, novel human-in-the-loop artificial intelligence technology.

This novel human-in-the-loop technology enables Roots Automation’s AI-powered Digital Coworkers to interact with human employees in real-time to raise and manage exceptions such as missing data, poor quality documents or a myriad of other exceptions that commonly occur within automated processes.

The ‘bot-to-human’ hand-off is a critical weak-point for traditional automation technology – in which, as a path to completing a process becomes blocked (i.e. an exception occurs), the bot will simply back-log the item for a human to review and process manually. Depending on the complexity of the process and the volume of exceptions, this can range from a day’s work for a process owner to complete to many days, dramatically disrupting an employee’s productivity.

Leveraging the human-in-the-loop artificial intelligence, Roots Automation’s Digital Coworkers interact with people via a simple user unified interface that uses Natural Language to ask a series of questions to extract the missing data, then re-process the item automatically.

“The technology is designed with the human in mind,” said CTO and co-founder John Cottongim. “The AI will effectively articulate its question, either prompting the user to answer from a selection of choices or even asking an open-ended question. The style and types of questions vary depending on the process, the outcomes and even the industry the Digital Coworker is operating within,” he continued. “Finally, Customers can opt to extend the medium of communication beyond the unified platform out into tools such as web-based apps or business communication tools, like Slack and Teams. The end-result is a tailored solution for each individual customer and/or process.”

Critically, after each successful interaction with a human, Digital Coworkers will update their knowledge with the newly acquired data from the interaction to ensure the exception is handled appropriately next time around. Further, this knowledge is also shared across the entire Root’s customer base for all customers to benefit from this learning.

The new human-in-the-loop AI technology is already in use for many Roots Automation Customers. One specialty risk transfer and care coordination entity realized over $600,000 in cost-savings after deploying human-in-the-loop AI-powered Digital Coworkers to process health claim forms. Today, Digital Coworkers process up to 30,000 claims each month while learning continuously from every interaction.

If the Digital Coworkers are unable to read part of a document while processing these claims, they will take a screen-grab of the document, send the image to a human coworker and ask for guidance on specific areas in question. Then, once the human employee provides guidance, the Digital Coworkers will re-read the entire document, apply the new knowledge and finish the task.

“The AI isn’t just sending you a link to a document – it’s extracting relevant information and leveraging that context to improve its ability to read and understand,” said Chaz Perera, CEO and co-founder. “The AI is able to utilize knowledge and context in other situations, and with other documents. Ultimately, our Digital Coworkers are replicating what humans are doing when they are unsure about something – they are raising their hand, asking a colleague, applying the new learning and retaining this knowledge for next time,” Perera finished.

“The ability to have a single, consistent human-in-the-loop experience that cuts across all of your processes is what really sets this technology apart. And that’s actually why we were able to get the patent on this,” said Cottongim. “By focusing on advancements that deliver more natural, more human-like experiences is key to delivering on our mission: to make work more human,” Cottongim concluded.

For comments or quotes, please contact Chris Gayner, VP Marketing at


About Roots Automation

Roots Automation brings together machine intelligence and human ingenuity in the form of advanced, intelligent Digital Coworkers.

Think of a Digital Coworker as your ideal employee – digitized.

Our Digital Coworkers are built with AI at their core and are able to think, read and intuit like a human. They are pre-trained to understand and interact with documents, systems and processes commonly found in Insurance, Healthcare and Banking. Their knowledgebase is perpetually expanding with learning federated across Customers. They are always on, ultra-secure and deliver ROI from day one.  

Digital Coworkers free your people of inefficient, repetitive, soul-destroying work – enabling them to be more creative, more collaborative and more innovative.

In essence, we make work more human.

Learn how we do this at:

What’s a Rich Text element?

The rich text element allows you to create and format headings, paragraphs, blockquotes, images, and video all in one place instead of having to add and format them individually. Just double-click and easily create content.

Static and dynamic content editing

A rich text element can be used with static or dynamic content. For static content, just drop it into any page and begin editing. For dynamic content, add a rich text field to any collection and then connect a rich text element to that field in the settings panel. Voila!

How to customize formatting for each rich text

Headings, paragraphs, blockquotes, figures, images, and figure captions can all be styled after a class is added to the rich text element using the "When inside of" nested selector system.

Fusce non convallis mi. Curabitur nec rutrum orci. Etiam vitae diam ut tellus venenatis ultricies. Fusce vitae ipsum sed urna tempor tempor et vitae dui.
Fusce vulputate molestie est

Fusce non convallis mi. Curabitur nec rutrum orci. Etiam vitae diam ut tellus venenatis ultricies. Fusce vitae ipsum sed urna tempor tempor et vitae dui. Aliquam nibh ante, tempus vel ultricies nec, tempus sed felis. Nullam et efficitur velit. Aenean odio nulla, facilisis a commodo eu, suscipit at augue.

Aliquam rutrum dui sapien. Aliquam pulvinar lectus accumsan est dictum, et faucibus justo ornare. Mauris placerat placerat consequat. Donec commodo consectetur nunc, et posuere orci lacinia sed. Duis mollis, eros quis porta laoreet, mi est euismod lectus, vitae volutpat quam enim congue tellus. Lorem ipsum dolor sit amet, consectetur adipiscing elit. Proin ornare laoreet consequat. Integer at accumsan lacus, eget ultricies augue. Vestibulum semper sapien at venenatis pretium. Integer nec iaculis lacus. Sed elit nisi, luctus sit amet vehicula nec, mattis nec purus. Nulla facilisi. Nam ornare in justo eget facilisis.

  • Praesent sit amet lectus quis metus sagittis tempor.
  • Sed mattis ipsum vitae turpis laoreet condimentum
  • Sed orci erat, rhoncus efficitur eros a, sollicitudin commodo tortor
  • Sed accumsan ex viverra est tincidunt bibendum a non nulla curabitur eget ligula mauris
  • Nam ut sagittis velit suspendisse ullamcorper quis lorem vitae hendrerit
  • Vivamus diam orci, dignissim ac nulla hendrerit, porttitor posuere risus

Cras vel leo mattis viverra tellus eget vestibulum est

  1. Praesent sit amet lectus quis metus sagittis tempor.
  2. Sed mattis ipsum vitae turpis laoreet condimentum.
  3. Sed orci erat, rhoncus efficitur eros a, sollicitudin commodo tortor.
  4. Sed accumsan ex viverra est tincidunt bibendum a non nulla curabitur eget ligula mauris.
  5. Curabitur sit amet auctor tellus, at scelerisque sem. In sit amet convallis arcu, id vulputate velit. Proin feugiat interdum nulla, eu malesuada massa commodo quis.
  6. Vivamus diam orci, dignissim ac nulla hendrerit, porttitor posuere risus.

Cras vel leo mattis viverra tellus eget vestibulum est

  • Etiam arcu metus, vestibulum et consequat sit amet, imperdiet at augue donec condimentum risus at consequat sollicitudin.
  • In sit amet nisi vitae odio tristique posuere integer vel magna dignissim, sodales mauris a, tempus odio nullam orci sapien, posuere non posuere et, laoreet vel velit.
  • Quisque eleifend tempor eros aenean et tempus neque nam ut porttitor velit maecenas consectetur, lacus at commodo efficitur, est neque tincidunt leo, et dictum nunc lorem a est.
  • Maecenas viverra turpis vitae eros tempus porttitor nulla tempor nunc eros, eu elementum arcu dapibus a etiam a tristique metus.

Share this post


Let's make work more human, together.
Contact Us