Background
Flotation App is a first-in-class application for control operators working at flotation plants. The app is driven by AI model that simulates conditions, material, plant equipment, and calculates the best possible outcome. The app is supposed to help operators to achieve better metallurgical performance and offload them from tedious job of defining control setpoints.
My role
The task was to deliver and explain the recommendations to the operators in real time, and prompt them to action. I was leading end-to-end product design process starting from discovery sessions, workflows, preparing prototypes, validating them and assisting with delivery.
That required carefully listening to users and domain experts feedback, working closely with cross-discipline team and contributing to prioritization, and making sure everybody are aligned on the direction product is going.
Solution
Discovery showed that operators’ job is hectic, their focus and attention is scattered across numerous screens with alarms. Any additional cognitive load would prevent usage of the app. I designed the UI in a way its structure resembles flotation circuit and highlights setpoints that require action from operator. This reduced time operator had to spend on figuring out what needs to be done.
A common problem for AI-related products is users thinking of the app as a "black-box". To avoid this, the app explains performance impact of the recommendations, what will happen with the performance in case the recommendations are used vs. if they are ignored.
Impact
The application helped to increase transparency of the underlying model and gain operators' trust. Once it happened we started receiving feedback and learned important insights about operators' jobs. The application also became one of the tools that descreases product implementation time.