Nikola Banovic
Associate Professor of Computer Science & Engineering, College of Engineering
Tutorial Overview
Focus: Using AI to critically assess outputs, check reasoning, and strengthen trust in findings.
This session would focus on using AI as a tool for review rather than solely for generation. Participants would practice checking results for plausibility, identifying possible errors or overclaims, and building habits for validation and reproducibility. This is especially important for avoiding misplaced confidence in AI-assisted work.
Possible hands-on activities:
- Ask AI to critique an interpretation of findings
- Cross-check whether a result matches the stated method or assumptions
- Generate a validation checklist for an analysis workflow
- Identify possible sources of bias, confounding, or error
- Review examples of flawed outputs and discuss how to catch them
Reminder: All attendees, please bring a laptop.
About the Series
This tutorial series introduces practical ways researchers can use AI to support common stages of the research workflow. Designed as a hands-on learning experience, the series focuses on approachable, real-world applications rather than abstract theory. Each session will combine brief framing, live demonstrations, and guided practice so participants can explore how AI tools may help with tasks such as refining research questions, working with data, conducting early-stage analysis, checking outputs, and communicating findings responsibly. The goal is to help researchers develop useful habits for integrating AI into their work in thoughtful, transparent, and effective ways.
For questions please message Kelly Psilidis: [email protected]