Accelerating Project Development in EECS 485 with Maizey

Department of Computer Science and Engineering

Problem

Professor DeOrio sought to supplement existing course resources like office hours and discussion forums for his large EECS 485 Web Systems course, by providing quick feedback and assistance to students for one of their projects.

Audience

The AI assistant was targeted to students working on Project 4 of EECS 485 Web Systems.

Outcome/Impact

  • Deepens Understanding: Students found the assistant’s responses helpful and were able to make progress on their projects.
  • Enhanced Office Hours: The assistant helped students make initial progress, making subsequent office hours interactions more meaningful and efficient.
  • Improved Efficiency: 40.1% of students said using the assistant instead of the course forum or office hours saved time, and 30.5% of students reported that using the assistant helped them code faster.
  • Accurate Responses: A concentrated scope allowed the assistant to achieve 100% accuracy on debugging queries, and higher than 90% accuracy for project specification, conceptual, and implementation/code suggestion queries.

Read more about the AI assistant in this research paper co-authored by DeOrio.