Indico Data releases industry-first large language model benchmark for document understanding tasks
Learn More
  Everest Group IDP
             PEAK Matrix® 2022  
Indico Named as Major Contender and Star Performer in Everest Group's PEAK Matrix® for Intelligent Document Processing (IDP)
Access the Report


Digital Mailrooms: Intelligent Process Automation Cleans out Email In-boxes

May 18, 2020 | Business, Financial Services, Insurance, Intelligent Process Automation

Back to Blog

As companies look to cut costs for centralized contact centers, they are increasingly looking for ways to encourage customers and prospects to interact with them in ways other than by phone, which is the most expensive avenue. As a result, corporate email in-boxes – also known as “digital mailrooms” – are being flooded with messages, driving companies to seek ways to develop processes that automate responses to them. 

These days, on any given company’s website, you’re often hard-pressed to find a phone number to call with a question. Instead, you’re encouraged to use support pages, FAQs, chat and yes, email. 

Read, understand & categorize emails

As a result, corporate email in-boxes are being flooded with messages. Somebody then has to look at each one, and that takes time.

Let’s take the example of a large financial services company that gets around 3,000 support requests coming in by email each day. The requests tend to break down into one of four categories:

  • A non-actionable request (no response needed)
  • Trade request
  • Account service request
  • Customer onboarding request

The company feeds its emails to a customer relationship management (CRM) system, from where support representatives pick up and read each message. After determining what the customer wants, the rep extracts pertinent information for input into a downstream processing system, to kick off the fulfillment process. Such information includes the customer name, address, email address, account number, and the request type.

For the sake of argument, let’s say it takes support reps an average of 10 minutes to deal with each email – a reasonable estimate given the amount of info they have to extract and re-enter. So, 2000 emails x 10 min. each adds up to more than 330 hours per day of processing time. If you divide that by an 8-hour work day, it means you need more than 40 reps doing nothing but responding to emails each day (and that doesn’t account for breaks).

Yet the ability to provide fast, accurate responses to all customer contact center interactions is critical, and email is no exception. “Customers interact directly with contact centers, which play a vital role in creating the brand image,” says a report on contact center software by the research firm MarketsandMarkets. “A negative experience can lead to loss of customers or clients.”

Applying intelligence to automate email processing

The report also accurately points out that companies are effectively applying artificial intelligence to aid in their efforts to respond effectively to customers. 

One example is how intelligent process automation (IPA) software can help companies digest and distribute the flood of mail from their corporate email in-boxes. IPA tools can help companies automate processes that traditionally require labor-intensive human interaction. 

IPA employs artificial intelligence technologies, including optical character recognition and natural language processing, that enable it to “read” documents much like a human would – even those that contain content in an unstructured format, like emails, PDFs and Word documents. Indico’s software, for example, can draw on a massive baseline of words and concepts it understands, then apply that understanding to different documents and use cases, a concept known as transfer learning. 

In the corporate email in-box case, an intelligent automation tool would be able to “read” an incoming email, discern what the topic is, then route it to an appropriate subject matter expert. For relatively simple matters, such as a change of address request, the IPA tool could extract the pertinent information, input it into an appropriate downstream system, and respond to the customer on its own with a canned email. 

An intelligent process tool can also extract and automate the handling of any attachments from an email, such as PDFs and Word documents. Here again the tool is smart enough to “read” the attachments and extract relevant data for input it into another downstream tool for processing or future reference, such as a customer relationship management (CRM) system.  

In either case, the IPA software could dramatically speed up the processing of thousands of emails, easing the burden on contact center personnel and freeing up their time for actually answering important emails. 

This is just one of many use cases where intelligent process automation can bring efficiencies to processes that to date have required hands-on (or eyes-on) human involvement.


Increase intake capacity. Drive top line revenue growth.


Get started with Indico

1-1 Demo



Gain insights from experts in automation, data, machine learning, and digital transformation.

Unstructured Unlocked

Enterprise leaders discuss how to unlock value from unstructured data.

YouTube Channel

Check out our YouTube channel to see clips from our podcast and more.
Subscribe to our blog

Get our best content on intelligent automation sent to your inbox weekly!