Home Bots & Business Case: Irish company saves 80% time with AI-enabled document processing

Case: Irish company saves 80% time with AI-enabled document processing

by Pieter Werner

Evros Technology Group has been delivering design, supply, implementation and IT infrastructure support services to clients for 30 years. Its offerings include managed IT services, cloud solutions, IT outsourcing, networking and security, technology recruitment, business continuity, and procurement solutions.

The Ireland-based company, which partners closely with global IT giants such as Microsoft, Dell, VMWare, Citrix and Hewlett Packard Enterprise, has doubled in size almost every three years since its inception.

“A large part of this is down to our ethos of working innovatively to firstly, enable our customers to work in the best way possible, and secondly give them the competitive edge they need to stand out within their market,” says Trevor Dagg, Head of Application Development.

“We want to ensure that we’re always able to provide our customers with everything they need. And this means having the skills, experience and expertise needed to deliver the most advanced technologies when the solution requires.”

Business automation

Evros first began evaluating business automation solutions in 2018.
“Over the last few years, we have been identifying software partners who have the right level of expertise to advance our offering. And as global leaders in Robotic Process Automation, UiPath was the natural partner of choice for this area.”

After implementing UiPath products on several IT projects, such as scaling infrastructure, streamlining patch management, and activating or deactivating customer service accounts, the team’s positive experiences led them to test UiPath on other enterprise use cases.

More specifically, how UiPath RPA and related technologies, such as UiPath Document Understanding and AI Fabric—which use RPA and AI to process documents and unstructured data—could solve challenges across the company and not just specific IT projects.

“We wanted to start implementing these tools within our own business so that we could benefit from them but also it was a chance to work innovatively, so that we could also discover the best ways to bring them all together,” says Dagg.


“We looked at a number of initiatives and ideas across the business including patch management, server ticket management, account activation and deactivation, and certain aspects of security.

“However, it was clear that we would have the biggest and most immediate impact by implementing RPA for our Finance Department, purely because of the number of repetitive, manual, low-exception rate tasks that they perform.”
After some initial investigation, the team discovered that finance team members were spending about 20 hours a week to process up to 1,800 invoices per month.

Their productivity was being hindered by manual document processing tasks that included scrolling through Microsoft Outlook emails to find and extract invoice attachments, printing the invoices, entering the information into Microsoft Dynamics NAV, and archiving the information upon completion.
Dagg says the finance team’s challenges presented a great opportunity for Evros to test the potential of products like UiPath Document Understanding and AI Fabric.


The Evros Application Development team initiated a careful planning process to ensure they captured all the needs of the finance team.

They looked at the volume of invoices to identify top suppliers, and at possible automation templates that would best capture the most common invoice data. Preferences of individual finance team members were considered. The IT team also evaluated the invoicing process to filter out other document types, such as credit notes.

“It’s important for any organization to sit down with the business team they are trying to help to understand and define their processes,” says Dagg. “We did a series of workshops with the finance team members and used UiPath Task Capture to cross check what the team was telling us.”

With the basic parameters established, Dagg explains the approach they took:

“Firstly, we mapped the business processes to an automated approach.

Using the invoice templates from our key suppliers we built and trained the data models.

Following that, we set up and configured UiPath Document Understanding along with UiPath AI Fabric feature.

The next step was to design and implement the integrations with Microsoft Outlook and Dynamics NAV (Evros financial system).

We then continued to improve the process through Machine Learning (ML).

The solution was configured to rank each scanned invoice to have a confidence score of 80% or more to continue its Happy Path for approval.


The documents that didn’t achieve 80% would be passed back to the Finance Team for update and correction using the solution. This would allow the data model to ‘learn’ and improve future confidence scores and increase number of successful automations.

And we also set up alerts and individual reports for each automation as well as a central report to highlight the overall performance of the solution using a Power BI dashboard.”

To implement the solution, Evros used UiPath AI Fabric, which helps deploy, consume, manage, and improve machine learning models. UiPath Document Understanding was leveraged to extract, interpret, and process the data collected from the invoices. The team also used UiPath Task Capture in designing the invoice processing workflows based on the actions on finance team users’ screens. Finally, deployment on UiPath Automation Cloud was preferred as an enterprise SaaS offering for RPA solutions.


The Evros team decided to use both unattended and attended bots as part of the invoice processing solution.

The unattended bots do most of the work, from capturing email attachments to reading invoice information and entering the data into appropriate fields in NAV. “When the solution was first implemented, there was a 60% level of confidence in how the bots were managing the information,” admits Dagg. “In 6-8 weeks, that number increased to around 80% and we expect it to improve further due to the continuous retraining on the human validated data.”

There are also attended bots. The Evros finance team members can run these each morning to review any problematic invoices and take appropriate action. “What’s really nice about using UiPath Document Understanding is that the finance team people can quickly view and cross check the invoices on a user-friendly screen, update content with necessary changes, and then apply the changes to move the invoice along its route into NAV,” says Dagg.

The beauty of using the UiPath products for the solution is that improvements to the invoice process lead to further insights and discoveries by the finance team—which lead to even faster and more efficient workflows.

Dagg says the IT department did some heavy lifting at the beginning of the project. However, the solution runs dynamically, so the finance team becomes more and more self-sufficient as they continually improve and refine the invoice processing using UiPath Document Understanding and AI Fabric.


The UiPath solution also delivered measurable benefits.

He says UiPath enabled Evros to create a solution that the finance team can continually scale with ease, which means they do not need as much help from the IT department as they used to in the past.

“Now we just have periodic touchpoints with them to see how they are getting along,” Dagg says. “The finance team is very happy with the initiative.”

Misschien vind je deze berichten ook interessant