AI/LLM Development Disclosure

Primary Uses of LLMs

As an educator focused on pedagogy and biological sciences rather than computer programming, I have leveraged AI assistants to:

• Translate educational concepts and scientific models into functional R Shiny applications through code generation
• Identify and resolve errors in R code
• Create intuitive, student-friendly interfaces appropriate for freshman-level biology students
• Properly implement ecological indices, statistical tests, and mathematical models
• Develop robust systems for data collection, storage, and retrieval across multiple user sessions
• Create clear, pedagogically effective graphs and charts using ggplot2 and plotly

Instructor Contributions

While AI provided technical implementation support, all pedagogical decisions and scientific content were developed by me, including educational objectives, biological models, research and experimental ideas, biological accuracy, and alignment with course curricula.

Development Process

My typical development workflow involved:

1. Defining educational goals and biological concepts to be demonstrated (e.g., learning objectives)
2. Describing desired functionality to the AI assistant in pedagogical terms
3. Using AI to generate initial R Shiny code based on specifications
4. Running applications with sample/simulated data and scenarios to discover bugs
5. Debugging by using AI to diagnose and fix issues discovered during use
6. Iterative refinement and other improvements based on my experience, classroom use, and some student feedback