AI Word Processor

Improving usability with AI tools for content writers.

A screenshot of Jenni's AI-powered word processor.

Overview

Client: Altum, Inc. (Startup)

Summary

  • Collaboratively created 6 crucial features to assist with faster article delivery.

Roles

  • UX Designer, UI Designer, User Researcher

Background

With complaints about our articles’ quality and delivery time, Altum looked to research, design, and test AI tools for its content writing service, Jenni AI, that would help improve Jenni’s word processor.

A dash list of text showing client complaints.
A list of client complaints we compiled into our sprint report.

Goals

We hypothesized that proper AI features would help content writers deliver high quality articles faster and decrease the number of client complaints about late articles.

Process

The steps of Altum's design process are:

  • Define. Defining our users and the MVP design.
  • Ideate. Ideating on design possibilities.
  • Test. Testing pre-release ideations.
  • Observe. Observing post-release outcomes.
A graphic showing a loop around Define and Ideate. Test and Observe aren't looped.
The Altum design process.

Define

Our first move was to interview content writers who noted issues such as:

  • Difficulties in adapting references into articles.
  • Lowering the plagiarism score.
Notes on the UX for one of Jenni's AI tools.
Excerpt of user interview notes regarding trouble with lowering the plagiarism score.

Ideate

I shared low and high-fidelity wireframes for feedback on each AI tool.

The AI tools addressed the various problems writers faced and addressed business needs as well.

A dialog box comparing two versions of text.
The Paraphrasing tool that restructured existing text into new plagiarism-free text.
Text highlighted in various colors with sidebar details.
The Readability tool tackled the issue of lowering plagiarism scores by giving writers clear feedback.
Text highlighted in green with previous versions in the sidebar.
The Simplifier also expedited lowering plagiarism scores by rewording input text to simplify it.
A paraphrasing tool currently in process of altering text.
The Scraper automated referencing articles by copying text directly into the word processor.
A dialog box letting users enter the article's title and primary keywords.
The Express modal, while not an AI tool, organized the AI tools in a more intuitive way.

Test

We optimized for the most results with the least investment by conducting budget usability tests.

Screen capture of a user inspecting two versions of text.
A screenshot of a user test with the subject completing tasks based on a scenario.

Observe

We tracked:

  • The number of late articles to measure writing time.
  • The number of client complaints.

Subsequently our results showed that:

  • Overall writing time didn’t go down.
  • The number of client complaints didn’t go down.

Reflection

The AI-Powered Word Processor didn’t meet its success metrics because the field of designing for AI usability is still new and the technology itself has a ways to go.

Excerpt of a report that lists issues relating to clients.
A sample of the many struggles Altum faced to improve Jenni’s AI tools.

Next steps

My next steps would’ve been to continue researching into improving the usability of our AI tools.

Let's get in touch!

Feel free to message me about any AI or UX-related jobs I can do for you.

I'd also love to learn about your favorite games and/or detective novels.

Connect on LinkedIn
^ Back to top