Teachers as Vibe-Coders: Authoring Adaptive Learning Simulators Through Natural Language

Gabrielle Anne Uy, Joseph Benjamin Ilagan, Jose Ramon Ilagan, Francine De Asis

In Adaptive Instructional Systems (HCII 2026), LNCS, pp. 558–568. Springer, 2026.

Download PDF (accepted manuscript) Published version (Springer)

Abstract

Learning simulations are effective pedagogical tools, but their development often requires technical expertise that limits direct teacher involvement in design. This paper examines how teachers can author adaptive learning simulators through natural-language interaction with AI, positioning educators as “vibe-coders” in teacher–AI co-design processes. Using a design-based research methodology, three teachers iteratively authored and deployed simulators across three undergraduate course contexts: Product Management and Costing, Service Management, and Solutions Architecture. Data were collected from teacher reflections, system interaction traces, and post-session surveys completed by students and teachers. Results indicate that teachers were able to construct functional, classroom-usable simulators through iterative prompt refinement, with domain characteristics shaping authoring effort, simulator behavior, and student sense-making. Students reported positive perceptions of clarity, usability, engagement, and learning support, while teacher reflections identified misalignment and constraint-setting as productive mechanisms for instructional refinement. The paper advances the concept of adaptive instructional authoring, re-framing adaptivity in educational systems as a design-time, co-creative process rather than solely a runtime property of learner-facing systems, and discusses design implications for natural-language authoring environments that preserve teacher agency in simulation-based higher education.

Keywords: Learning simulations; Generative AI; Vibe-coding; Natural-language authoring; Adaptive instructional systems; Teacher–AI co-design; Simulation-based learning

About this copy

Accepted manuscript. This version of the contribution has been accepted for publication, after peer review (when applicable) but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: http://dx.doi.org/10.1007/978-3-032-30015-7_35. Use of this Accepted Version is subject to the publisher’s Accepted Manuscript terms of use https://www.springernature.com/gp/open-research/policies/accepted-manuscript-terms.

Cite as

Gabrielle Anne Uy, Joseph Benjamin Ilagan, Jose Ramon Ilagan, Francine De Asis (2026). Teachers as Vibe-Coders: Authoring Adaptive Learning Simulators Through Natural Language. In Adaptive Instructional Systems (HCII 2026), LNCS, pp. 558–568. Springer. https://doi.org/10.1007/978-3-032-30015-7_35