What's the technology that powers Orion?

Let's take a glimpse under the hood of this customer service automation engine.

Artificial Intelligence (AI) and Natural Language Processing

Orion is built on natural language processing (NLP) technology. NLP is a subfield of artificial intelligence. NLP touches upon two umbrellas of techniques namely machine learning (ML) and deep learning (DL).

A fast moving technological field

Every day, new innovation is happening in the AI domain. Since the launch of the open-source machine learning library Tensorflow in 2015 new libraries, platforms and techniques developed by a variety of research centers, universities and organisations are popping up every 3 months.

Our best-of-breed vision

It is our vision to master the various state-of-the-art technologies out there, in order to bring a best-of-breed mix to the table. This allows us to stand on the shoulder of giants and deliver the best possible results to power customer service needs.

Our competency

Staying up-to-date on latest developments and putting together the right mix of technologies and techniques is our competency. Combining computer science with our experience in the customer service domain together with the ability to integrate, is what makes Orion today.

A custom built AI model for each Orion client

The basis of customer service automation is the ability to automatically recognise customer questions. Everything else follows from that.

Custom AI models

What sets us apart is that we provide a tailor-made recognition model for each of our client organisations. This is how we are able to achieve the higher levels of recognition and are able to automate more.

Communication channels

Under the hood we build 1 model per language that can handle a variety of digital text channels.


Using our proprietary technology for e-mail we can extract the essential paragraph from an e-mail thread.


Webforms and contactforms are among the cleanest forms of customer question input.

The special case of e-mail

You might not be aware, but e-mail is a particularly hard nut to crack when it comes to natural language processing.

What's the difficulty?

Most e-mails are not stand-alone but are part of a thread. They are replies, forwards and replies again on some original mail.

From the perspective of a machine, it's not straightforward to find the essence of the e-mail.

How humans do it

As humans we know to scroll through an e-mail thread, check who replied to who and find the main question, while ignoring the other stuff such as headings, footers and markup.

Orions mastery of e-mail

Over the years we have developed a specific and proprietary algorithm able to extract the essential question paragraph of an e-mail thread. It works across a variety of e-mailing styles, languages and mixes of plain-text or html formatted e-mails.

Under the hood: powerful pre-processing

Garbage in = garbage out

If you just input any kind of text into an AI model the result is in 99% of cases useless. "Garbage in, garbage out" as we sometimes say. Reason is that such models do not know what parts of text to focus on. This we want to avoid.


Since the style and structure of an e-mail question differs from a contactform, which again varies from a chat message, our first step is to transform that. This is what we call pre-processing the input.

Feeding the model

The pre-processing allows us to make abstraction of the original channel and feed the processed question input into the single recognition model we have custom built for each of our clients. The recognition approaches the state of the art.