Wendy's X Google Cloud
As a Creative Technologist Intern at Deeplocal, I contributed to the development of interactive exhibitions for the Google Cloud Next 2023 conference. One notable project that I worked on was the “Wendy’s x Google Cloud” exhibit, which showcased Wendy’s Fresh AI, a conversational AI platform utilizing voice recognition technology powered by Google’s Vertex AI.
In this project, I was responsible for designing and building a logging system to facilitate easier debugging and benchmarking for usability tests. This role provided valuable insights into industry best practices and the integration of AI models for assistive voice user interfaces (VUI).
Position:
Creative Technologist Intern at Deeplocal
Role:
Designing and building a logging system to facilitate easier debugging and benchmarking for usability tests
Tools Used: Node.js, Google Vertex AI API
Team Lead:
Sean Scanlan & Blair Neal
Client:
Google Cloud Next’23 Conference
As a Creative Technologist Intern at Deeplocal, I contributed to the development of interactive exhibitions for the Google Cloud Next 2023 conference. One notable project that I worked on was the “Wendy’s x Google Cloud” exhibit, which showcased Wendy’s Fresh AI, a conversational AI platform utilizing voice recognition technology powered by Google’s Vertex AI.
In this project, I was responsible for designing and building a logging system to facilitate easier debugging and benchmarking for usability tests. This role provided valuable insights into industry best practices and the integration of AI models for assistive voice user interfaces (VUI).
Position:
Creative Technologist Intern at Deeplocal
Role:
Designing and building a logging system to facilitate easier debugging and benchmarking for usability tests
Tools Used: Node.js, Google Vertex AI API
Team Lead:
Sean Scanlan & Blair Neal
Client:
Google Cloud Next’23 Conference
User Experience Goal:
The goal of this exhibit was for users to experience what ordering at a Wendy’s drive-through powered by voice recognition AI assistance would be like. The Voice User Interface (VUI) needed to understand menu items and colloquialisms such as “JBC” for Junior Bacon Cheeseburger and “milkshake” for Frosty. Additionally, the VUI microphone system needed to work effectively at a range of distances. To ensure the installation could handle edge case scenarios at the final Google Next ’23 Conference event, extensive usability testing was necessary.
The goal of this exhibit was for users to experience what ordering at a Wendy’s drive-through powered by voice recognition AI assistance would be like. The Voice User Interface (VUI) needed to understand menu items and colloquialisms such as “JBC” for Junior Bacon Cheeseburger and “milkshake” for Frosty. Additionally, the VUI microphone system needed to work effectively at a range of distances. To ensure the installation could handle edge case scenarios at the final Google Next ’23 Conference event, extensive usability testing was necessary.
The Challenge:
The challenge was to streamline the usability testing process for Wendy’s Fresh AI, which required handling large volumes of data generated by the AI’s interactions with users. The existing system needed enhancements to efficiently log and interpret these interactions to identify areas for improvement and ensuring smooth functioning of the exhibit at the event.
The challenge was to streamline the usability testing process for Wendy’s Fresh AI, which required handling large volumes of data generated by the AI’s interactions with users. The existing system needed enhancements to efficiently log and interpret these interactions to identify areas for improvement and ensuring smooth functioning of the exhibit at the event.
Role and Responsibilities:
In this project, I was responsible for designing and building a logging system to facilitate easier debugging and benchmarking for usability tests. This involved:
- System Development: Using Node.js and the Google Vertex AI API to develop a robust logging system.
- Debugging and Benchmarking: Creating a system that allowed for efficient tracking and debugging of the AI’s responses during usability testing.
- Data Conversion: Ensuring that the system could handle massive asynchronous orders, converting machine-readable JSON outputs into human-readable formats for analysis.
Key Features and Solutions:
- Integration with Fresh AI: The logging system was directly connected to Wendy’s Fresh AI LLM model. Each time a user placed an order, the system communicated with the LLM model and received responses formatted as JSON outputs.
-
Asynchronous Processing: Designed to handle large batches of orders asynchronously, ensuring the system could process data in real-time without delays.
-
Human-Readable Outputs: Converted the machine-readable JSON data into human-readable formats, making it easier for the team to analyze and interpret the results.
- Usability Testing Enhancement: Facilitated more efficient and effective usability testing, allowing the team to quickly identify and address any issues with the AI’s performance.
Impact and Insights:
This role provided valuable insights into industry best practices and the integration of AI models in real-world applications. The project highlighted the growing importance of AI-assisted voice user interfaces (VUI) and their potential to transform user interactions in various applications. By developing a logging system, I contributed to enhancing the overall usability and effectiveness of the Wendy’s Fresh AI exhibition.