Aiaibot
Aiaibot makes it easier for enterprise companies, automating their customer dialogues at all digital touchpoints and ensuring both - more efficiency in their processes and a higher quality of services.
Role
UI/UX Designer
Team
Front & Back End Developers, Product Manager, QA Engineers
Industry
IT, Machine Learning
Year
2020
Overview
Business Goal
Normally, the use of such Machine Learning algorithms and the training of classifiers require very specific know-how and expert knowledge. One of the goals in developing aiaibot is therefore to simplify this process and make it accessible to more people. Based on the feedback from our customers, I believe we have achieved this goal.
"The biggest challenge in the implementation of customer projects is the ability to provide high-quality training data in sufficient quantity."
User Need
This has a crucial influence on the results that our customers can achieve. To pinpoint the problem, we had to make sure that the user which had a model evaluated, can see and understand its performance. We wanted to visually guide the users through the process, and introduce them to more advanced key metrics, to get the full advantage of the tool.
The Process
Acquire Knowledge
Based on the experiences of our previous research team and the development of the on-premise solution lena by PIDAS, we had the chance to include their knowledge into a new mission and vision for a scalable and dynamic product.
User's Pain Points
File import on Lena was too complicated.
Unintuitive and complex Ul/ UX in the report area. Users shared their frustration about how informations where shown.
On Lena classifiers had to be activated first, before you can use them. This creates some friction.
We had a list of all trainings of a classifier, and the user had to specifically select a certain training, this creates un-necessary work.
Personas
Target
Aiaibot is primarily focusing on Enterprises, larger organizations relying on NLP-powered workflows to automate processes, requiring scalable, robust, and easily configurable solutions for their business use cases.
Analysis
During the user research, which led us to create personas, a common pain point across multiple user types is the fact that they struggle to import files and set up classifiers effectively, leading to frustration. On top of that, the report section had unintuitive displays, making it hard for users to interpret key metrics (e.g., confusion matrix) or understand how to leverage them.
Business Goal / User Need Fit
Simplify the NLP tool for non-expert users while maintaining flexibility for advanced users, ensuring high adoption, retention, and scalability. By creating intuitive workflows for file uploads, optimize the UI for data visualization and streamlining redundant processes to ensure a smooth user journey, saving time and reducing onboarding hurdles.
Prototype
Goal
One of the main goals in developing aiaibot is therefore to simplify this process and make it accessible to more people. Based on the feedback from our customers, I believe we have achieved this goal.
Solution
The outcome is a powerful, easy to use and simple to integrate platform that allows users to efficiently train a state-of-the-art multilingual machine learning model on their own data with just three clicks. I collaborated closely with the machine learning engineering team to break down complex ideas and communicate them visually in a clear and consistent manner.
Considerations
Moreover, our designs had to be thought through completely from the start because the front end was implemented by a third party and later changes were costly. That meant that I also conducted quality assurance and guided our overseas contractors. I believe that our part of the product has an appealing UI/UX that helps the users to achieve their goals.
Conclusions
Impact of the solution
The NLP (Natural Language Processing) solution has revolutionized user interactions by enabling more intuitive, context-aware conversations that feel natural and personalized. By leveraging machine learning, we enhanced the bot's ability to understand and respond accurately to diverse user inputs, driving better engagement and improving the overall user experience.
Storybook for consistency
In order to ensure consistent user experiences across the different tools available on the platform, we kept our components up-to-date and documented in Storybook.
A solution that helped designers & front ends to be on the same page and re-use components to increase efficiency.
Final thoughts
I conducted quality assurance on overseas third parties contractors working on Github, making sure that the delivery was as expected.
It was a great challenge and I'm really grateful for all the feedback we got from users over time. Thanks to that, we made sure to shape the product on their needs, increasing the success rate on their tasks.
