DESIGN AND VALIDATION OF A LANGCHAIN-BASED INSTRUCTIONAL AGENT FOR REAL-TIME SUPPORT IN COMPUTER SCIENCE LABORATORIES
DOI:
https://doi.org/10.71146/kjmr941Keywords:
Instructional agent, LangChain, AI in education, Computer Science laboratories, real-time support, questionnaire validationAbstract
The paper describes the structure and testing of an instructional agent powered by LangChain on a real time basis and used in Computer Science laboratory lessons. The suggested agent incorporates timely templates, chat memory, a layer of academic-integrity policies in order to provide scaffolded advice (by giving hints, reasoning checks, and validation processes) instead of directly dumping answers. Responsiveness, explanation clarity, debugging support, usability, perceived accuracy and overall satisfaction were measured using a quantitative instrument (5-point Likert). The results provided are furnished (N=120; illustrative) with high means of construct (4.19-4.40/5), high internal consistency (overall Cronbach a=0.89), and high rate of agreement in satisfaction and recommendation (78 percent). In addition to descriptive result, the presented items of the study provide item-total correlations, exploratory factor structure, inter-construct correlations, and a predictive regression model of satisfaction, which is consistent with the typical psychometric and technology acceptance validation procedures [3-6, 9-13].
Downloads
References
[1] J. R. Anderson, The Architecture of Cognition. Harvard University Press, 1983.
[2] B. P. Woolf, Building Intelligent Interactive Tutors. Morgan Kaufmann, 2010.
[3] F. D. Davis, “Perceived usefulness, perceived ease of use, and user acceptance of information technology,” MIS Quarterly, 1989.
[4] V. Venkatesh and F. D. Davis, “A theoretical extension of the technology acceptance model,” Management Science, 2000.
[5] V. Venkatesh, M. Morris, G. Davis, and F. Davis, “User acceptance of information technology: Toward a unified view,” MIS Quarterly, 2003.
[6] O. Zawacki-Richter, V. Marín, M. Bond, and F. Gouverneur, “Systematic review of AI applications in higher education,” Int. J. Educ. Tech. Higher Educ., 2019.
[7] ISO 9241-11, “Ergonomics of human-system interaction — Part 11: Usability,” ISO, 2018.
[8] J. Nielsen, Usability Engineering. Morgan Kaufmann, 1993.
[9] J. C. Nunnally and I. H. Bernstein, Psychometric Theory, 3rd ed. McGraw-Hill, 1994.
[10] L. J. Cronbach, “Coefficient alpha and the internal structure of tests,” Psychometrika, 1951.
[11] J. W. Creswell and J. D. Creswell, Research Design, 5th ed. SAGE, 2018.
[12] A. Field, Discovering Statistics Using IBM SPSS Statistics, 5th ed. SAGE, 2018.
[13] T. A. DeVellis, Scale Development: Theory and Applications, 4th ed. SAGE, 2016.
[14] R. Likert, “A technique for the measurement of attitudes,” Archives of Psychology, 1932.
[15] J. Sweller, “Cognitive load during problem solving,” Cognitive Science, 1988.
[16] J. Hattie, Visible Learning. Routledge, 2009.
[17] B. S. Bloom, “The 2 sigma problem: The search for methods of group instruction as effective as one-to-one tutoring,” Educational Researcher, 1984.
[18] K. VanLehn, “The relative effectiveness of human tutoring, intelligent tutoring systems, and other tutoring systems,” Educational Psychologist, 2011.
[19] S. Russell and P. Norvig, Artificial Intelligence: A Modern Approach, 4th ed. Pearson, 2020.
[20] T. Brown et al., “Language models are few-shot learners,” NeurIPS, 2020.
[21] J. Wei et al., “Chain-of-thought prompting elicits reasoning in large language models,” 2022.
[22] OpenAI, “GPT-4 Technical Report,” 2023.
[23] S. Bubeck et al., “Sparks of artificial general intelligence: Early experiments with GPT-4,” 2023.
[24] Harrison Chase, “LangChain documentation: Building applications with LLMs,” 2023.
[25] B. Means et al., “Evaluation of evidence-based practices in online learning,” U.S. Department of Education, 2010.
Downloads
Published
Issue
Section
Categories
License
Copyright (c) 2026 Shahbaz Ahmad Sahi, Ali Raza, Shahzad Nazir (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
KJMR publishes all articles as open access under CC BY 4.0, allowing anyone to share and adapt the work, even commercially, with proper credit, a license link, and clear notice of changes, without implying endorsement. Authors retain copyright while granting the journal non-exclusive publishing and archiving rights and may self-archive without embargo. Third-party material requires proper permission, and the journal ensures long-term free access through its website and archiving partners.
How to Cite
