The New Narrative 

Want to know what makes us different? This is a great place to start. See how we’re innovating and experimenting, constantly. And get our take on the ideas of the moment— and where we think tomorrow will take us—across the industry and around the world. 


5 Questions to Ask Yourself When Deploying Automation

For most people we engage with, the term and concept of Advanced Natural Language Generation (Advanced NLG) is new. We are often tasked with helping our customers think through the business impact of automatically transforming data into narratives and educating them on the best practices for getting the most value.

So, how should you think about your Advanced NLG project? For many of our clients, the goal usually falls into one of three camps.  

  1. Automating an existing process that humans do, freeing up resources and enabling scale,
  2. Creating a new product or product feature that can be monetized by expressing the knowledge locked within proprietary data, or
  3. Adding relevant and action-oriented insight to each and every customer interaction, enabled through data

The first step is to determine your business goal. While that sounds obvious, people often have a tough time defining what they want from data. A common misconception is, “I'm going to throw my data into this  black box, and it will magically unearth all the answers to my toughest business problems.” But, think about how an analyst would approach finding an answer to a problem. He would start with the question he is trying to answer and then use data to find and support the answer. In reality, Advanced NLG systems function the same way. Once they know what you want to communicate, to whom and why, they can scale the thinking and process of your best analysts and automatically create the identified report or communication.

The next phase is to think through what makes for good content, as well as make the case for automation in your business. Given our roots at Northwestern’s Medill School, Quill utilizes the core principles of journalism and writing best practices, including the who, what, where, when, and why of telling an informative story.

It’s important to determine how these ideas will be incorporated into the project you’re looking to undertake. Once these questions are answered, the automation piece is easy.

1.Who is the audience?

Who is consuming this content, and what action will they be able to take?

Why does this person need the analysis of the data?

2. What type of content are you automating?

What is your vision for the content that will be automated? Is it being created today or will it be something entirely new?

How much of the content is designed to interpret data? How much of it is to articulate factors that exist outside of the data?

What is your process now to access, manage, and interpret data across different internal and external functions?

3. Where will the person access or interact with this information?

What is the typical process for getting this information? Is it extracted from a dashboard or portal, or is the content distributed manually?

4. When will they be interacting with the content?

Will the content be refreshed regularly, like a weekly, monthly, or quarterly report, or does it need to be available “on-demand?”

Does the frequency or speed requirements of the reporting make it inefficient for humans to handle the task today?

5. Why are you automating?

How will you measure improvement from this new automated process?

Who is going to be most interested about the impact of this automation? Your CFO? Head of Sales? Both?

Now you are prepared to have success with your Advanced NLG project! And of course if you need a helping hand, our team is always at the ready.

For more information on how other businesses are already applying Advanced NLG, read: The Automated Analyst: Transforming Data into Stories with Advanced NLG


Privacy Policy | © 2017 Narrative Science