Is this project an undergraduate, graduate, or faculty project?

Undergraduate

Project Type

group

Campus

Daytona Beach

Authors' Class Standing

Tsumir Babakhanau, Senior Noah Clark Colby Keller Mary Grace Sorenson Zoe Tiede

Lead Presenter's Name

Tsimur Babakhanau

Lead Presenter's College

DB College of Arts and Sciences

Faculty Mentor Name

Barbara Chaparro

Abstract

This study implements a detailed naval scenario in which participants acted as operators on a Navy destroyer equipped with a Laser Weapon System (LaWS). Their task was to create a dashboard capable of stopping incoming suicide drone swarms while managing critical laser functions such as thermal constraints, threat prioritization, and adapting to attack dynamics. Poor management could leave the ship vulnerable. AI is increasingly integrated into design methods, fundamentally transforming the process of building user interfaces by compressing hours of work into minutes. Although AI design tools are becoming more common, little is known about how well beginners can use these systems in terms of time, quality, and task performance. A convenience sample of 31 students was randomly assigned to either a manual condition (paper and pencil or Figma) or an AI-assisted condition (Figma Make, Claude, or DeepSeek), with 50 minutes to complete their interface. Completion time was recorded, and participants completed a post-task survey measuring perceived performance, ease, and confidence. Both design mediums were analyzed through the maintenance of key elements, military standards, and human factor principles. Preliminary survey responses indicate that AI-assisted tools facilitated quicker idea generation and outcomes relative to manual methods, which required participants to invest significantly more time in repetitive tasks. However, AI users often felt limited in their creativity, indicating that while they were more productive, their success sometimes came with drawbacks such as stifled thoughts and a lack of personal expression. These findings have implications for integrating AI tools into novice design workflows and may inform future research on the relationship between tool type, creativity, and design outcomes.

Did this research project receive funding support (Spark, SURF, Research Abroad, Student Internal Grants, Collaborative, Climbing, or Ignite Grants) from the Office of Undergraduate Research?

No

Share

COinS
 

Designing Under Pressure: A Comparative Study of AI and Manual Interface Development in a Naval Weapon System Scenario

This study implements a detailed naval scenario in which participants acted as operators on a Navy destroyer equipped with a Laser Weapon System (LaWS). Their task was to create a dashboard capable of stopping incoming suicide drone swarms while managing critical laser functions such as thermal constraints, threat prioritization, and adapting to attack dynamics. Poor management could leave the ship vulnerable. AI is increasingly integrated into design methods, fundamentally transforming the process of building user interfaces by compressing hours of work into minutes. Although AI design tools are becoming more common, little is known about how well beginners can use these systems in terms of time, quality, and task performance. A convenience sample of 31 students was randomly assigned to either a manual condition (paper and pencil or Figma) or an AI-assisted condition (Figma Make, Claude, or DeepSeek), with 50 minutes to complete their interface. Completion time was recorded, and participants completed a post-task survey measuring perceived performance, ease, and confidence. Both design mediums were analyzed through the maintenance of key elements, military standards, and human factor principles. Preliminary survey responses indicate that AI-assisted tools facilitated quicker idea generation and outcomes relative to manual methods, which required participants to invest significantly more time in repetitive tasks. However, AI users often felt limited in their creativity, indicating that while they were more productive, their success sometimes came with drawbacks such as stifled thoughts and a lack of personal expression. These findings have implications for integrating AI tools into novice design workflows and may inform future research on the relationship between tool type, creativity, and design outcomes.

 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.