Intelligence Augmented Interfaces are becoming more popular nowadays. Within this project I dealt with the design of an interfaces which allowed machines to learn and draw the right conclusions from human behavior.
- Heuristic Evaluation
- User Research
- UX Wireframing
- UI Visualization
Due to a non-disclosure agreement I have to be a bit abstract when talking about this project. My client developed an algorithm, which evaluates textual content by identifying certain keywords and analyzing their contextual meaning. Based on its evaluation the algorithm will output a score, identifying the importance of the text analyzed.
To improve the confidence of the algorithm, it required user feedback on its scorings. As the first version was built without design involvement, the interface was limited in its feedback possibilities. The project’s challenge was consequently uniting data science requirements with user behavior and needs.
I started the project with a heuristic evaluation of the existing interface. Such analysis allowed me to identify obvious design flaws in usability and gestalt. I ended up recording a list of 50 instances, including major flaws such as missing friction for crucial actions as well as minor issues in the visualization like consistent link styling. Together with the development team, I further analyzed the current back- and frontend restrictions, to increase the awareness of those during the design process.
My research phase was split into two parts. On the one side I had to understand the feedback required by the algorithm to improve itself. On the other hand, it was crucial to understand the daily workflows of the users and how the product integrated into these. I therefore conducted qualitative, exploratory interviews with data scientist as well as existing users. During the user interviews, I focused on identifying their direct and indirect ways of feedback. Later in the project we also profited strongly from the gained trust and personal relationship.
Based on the learnings from research and the heuristic analysis, I created an initial set of wireframes. The users were then asked to test and evaluate a clickdummy within a workshop held at their premises. Finally the group prioritized the features for further design and development.
Consequently, the wireframes evolved into a high-fidelity interface. The designs used the corporate identify and existing design system, whereby I also got the freedom to criticize and improve the client’s design system. I then prepared the specifications and required assets to hand over the final product to the development team.
I see the design of products which mediate between artificial intelligence and human behavior as a fascinating yet challenging field, which I hope to focus more on in future. The project is currently being implemented, although the client decided to prioritize the scaling of its backend capabilities over the redesign of the product’s frontend.