2026 ASEE Annual Conference & Exposition

Integrating Generative AI Chatbots to Foster the Entrepreneurial Mindset in Engineering Education

Presented at Computers in Education (CoED): Learning, Engagement & Inclusion (1 of 9) -- M308B

Generative AI offers a scalable way to support the Entrepreneurial Mindset (EM: Curiosity, Connections, and Creating Value) in engineering education, yet many classroom deployments rely on generic chat interfaces that deliver technical answers without prompting EM related reflection. This study evaluates a custom Retrieval Augmented Generation (RAG) chatbot deployed across four engineering courses at a public research university. A distinguishing feature is an optional “EM Info Box” that appends a short, structured metacognitive prompt to selected technical responses. We analyzed n = 3,187 interaction turns from a 16 week semester using log based observational methods. Generalized Estimating Equations modeled the association between EM aligned responses and immediate follow up behavior while accounting for within-student clustering, complemented by a longitudinal analysis of prompt length. Because the EM Info Box is activated by a content based classifier rather than randomized assignment, all reported effects are associative.
Findings indicate that EM aligned scaffolding varies by disciplinary context: in one course, EM aligned turns were associated with lower follow up probability, suggesting single turn informational resolution. In another, ``Creating Value'' triggers reframed technical metrics as expressions of stakeholder value. Longitudinal patterns revealed modest within-student growth in prompt length with a spike near a major deadline. These findings provide behavioral trace evidence of when EM aligned scaffolding appears and how it co-occurs with interaction behaviors, without directly measuring changes in students' underlying mindset.

Authors

Xing Gao University of Illinois at Urbana - Champaign [biography]

Xing Gao is a Master student in Computer Science at the University of Illinois at Urbana-Champaign. She holds a Bachelor of Science in Computer Science from University of Delaware. Her research focuses on knowledge graph optimization with LLMs for personalized learning.
Abdulrahman AlRabah University of Illinois at Urbana - Champaign [biography]

Abdulrahman AlRabah is a Ph.D. student in the Siebel School of Computing and Data Science at the University of Illinois Urbana Champaign, where he also earned his M.S. in Computer Science. He received his B.S. in Mechanical Engineering from California State University Northridge and has industry experience including oil and gas and co founding a food and beverage company. His research focuses on AI for computing education, using customized large language models and learning analytics, including knowledge graph based concept modeling, to deliver better feedback, improve student learning, and support instructors.
Dr. Sotiria Koloutsou-Vakakis http://orcid.org/0000-0002-7658-6517 University of Illinois at Urbana - Champaign [biography]

Dr. Sotiria Koloutsou-Vakakis holds a Diploma in Surveying Engineering (National Technical University of Athens, Greece), a M.A. in Geography (University of California, Los Angeles), and M.S. and Ph.D. degrees in Environmental Engineering (University of Illinois Urbana-Champaign). Her interests include air quality, environmental policy, and supporting student learning and professional development.
Prof. Tomasz Kozlowski http://orcid.org/0000-0001-9317-5309 University of Illinois at Urbana - Champaign [biography]

Dr. Tomasz Kozlowski is a Professor and Associate Head for the Undergraduate Programs in the Department of Nuclear, Plasma, and Radiological Engineering at the University of Illinois Urbana-Champaign. He received a Ph.D. in Nuclear Engineering from Purdue University in 2005, where he worked on spatial homogenization methods for neutron transport calculations, multi-physics coupling, and PARCS code development. Dr. Kozlowski has been an instructor in professional workforce development courses and summer schools, including MeV, FJOH, SUNCOP, and NRS-HOT (since 2006). He has been an active member of the American Nuclear Society (since 1997) and the American Society for Engineering Education (since 2016). He is a member of the OECD/NEA Nuclear Science Committee Working Party on Reactor Systems (NSC/WPRS) (since 2010) and is serving on the Scientific Board and Technical Committee of the OECD/NEA Benchmark for Uncertainty Analysis in Best-Estimate Modelling for Design, Operation and Safety Analysis of Light Water Reactors (LWR-UAM) (since 2008). He is an Associate Editor of Nuclear Technology (since 2021) and has been a reviewer for several journals in the fields of nuclear engineering, fluid flow and heat transfer, and uncertainty quantification (since 2006).
Dr. Volodymyr Kindratenko http://orcid.org/0000-0002-9336-4756 University of Illinois at Urbana - Champaign [biography]

Volodymyr Kindratenko is the Director for the Center for Artificial Intelligence Innovation (CAII) at the National Center for Supercomputing Applications (NCSA). He is also an Adjunct Associate Professor in the Departments of Electrical and Computer Engineering and a Research Associate Professor in the Siebel School of Computing and Data Science. His research interests lie at the intersection of AI systems and applications, with a focus on generative AI solutions for science and education. His team is developing the uiuc.chat chatbot platform, which facilitates rapid knowledge distillation.
Dr. Abdussalam Alawini University of Illinois Urbana-Champaign [biography]

Dr. Alawini is a Teaching Associate Professor in the School of Computing and Data Science at the
University of Illinois at Urbana-Champaign. He holds a bachelor’s degree from the University of Tripoli
and master’s and doctoral degrees in Computer Science from Portland State University. His research focuses on data management systems and computing education. Dr. Alawini is passionate about building data-driven, AI-based systems for improving teaching and learning.

Note

The full paper will be available to logged in and registered conference attendees once the conference starts on June 21, 2026, and to all visitors after the conference ends on June 24, 2026

« View session