HPE
My Role
Designing an AI-Powered Application to Prevent Illegally Sourced Precious Metals from Entering the Supply Chain
Leveraging AI visual recognition technology, we developed a solution that allows users to take a picture of a gold bar to register it, authenticate its origin, and track it from source to vault. This innovative approach enables secure provenance tracking, contributing to sustainable mining practices and ethical sourcing.
Problem Statement
Illegal mining has devastating effects on the environment and local communities, leading to increased deforestation, mercury contamination, river sedimentation, land appropriation, and escalated violence. Our challenge was to design an application that would support miners and logistic operators in documenting the journey of gold, ensuring the integrity of the supply chain while overcoming limited access to end users and differing assumptions about the app’s purpose among cross-functional teams.
Design Process
Research & User Definition
Collaborating with product managers, developers, and designers, I facilitated workshops to bring all stakeholders into the design process. These sessions allowed us to articulate and validate assumptions about user personas and goals, aligning teams around shared objectives for usability and functionality.
Through our workshops, we established four criteria for persona development:
Through our workshops, we established four criteria for persona development:
Miners
Responsible for registering gold at the source
Logistics Operators
Track and transport gold throughout the supply chain.
Refiners
Verify and process the gold at later stages.
Storytelling
To ensure cross-functional understanding, I created storyboards and process flow based on contextual inquiries. I mapped the user journey to highlight pain points and opportunities for our solution to alleviate them. This method allowed stakeholders to step into users’ shoes and empathize with their experiences, aligning the team around a cohesive conceptual model before moving to wireframe.
First Phase
Creating a MVE (Minimal Viable Experience)
With the help of the product owner, developers, and QA engineers, we brainstormed to determine usability goals and define the main elements and actions the application should provide for the first release.
Defining Usability Goals
Defining Objects and Actions
Ideation
I created low-fidelity wireframes to validate assumptions with my team.
First Iteration
The first iteration allows users to scan a radio frequency tag attached to the gold bullion. The application shows key inventory management metrics and easy access to the most common actions.
Ergonomic considerations
Knowing that our users would perform repetitive tasks in an industrial environment, it was essential to consider the position of the buttons on the screen to facilitate easy access to the most common actions.
Second Iteration
After testing the concept and branding with subject matter experts and based on their feedback, I redesigned the solution with a different visual and interaction approach where KPIs were more prominent and the color palette and user interface components looked cleaner.
Final Solution
Prototype
Design Impact
Second Phase
Improving User Experience With AI Visual Recognition
A radio frequency seal can be easily tampered with. It requires that our users manually attach the seal to the gold bar, and they have to do that to hundreds of bars. Here is where AI can help to automate this repetitive task and improve the security of the supply chain.
Problem Framing
We identified a security vulnerability based on our research and experiences with the app’s initial version. We recognized that requiring users to attach physical seals to each gold bar was cumbersome.
Our main objective was to eliminate the repetitive task of applying physical seals to every gold bar while enhancing the supply chain’s security.
Ideation
Now that visual recognition can help to easily identify every gold bar based on its distinct qualities, users can focus on other tasks and jobs, such as the journey of the shipments they send and receive.
Workflow to identify tasks to automate with AI
Example of Brainstorming Ideas Through Sketching
Proof of concept
After brainstorming, I created a proof of concept for the developers and the product manager. I did this at the end of my time in Quenta, and I don’t have any information on the next stage of this initiative.
Challenges Faced
With this project, I had to learn the foundations of two different technologies, blockchain and AI visual recognition, so I could actively participate in brainstorming sessions with cross-functional teams and provide ideas to improve the product.