Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Co-designing Large Language Model Tools for Project-Based Learning with K12 Educators

Prerna Ravi, John Masla, Gisella Kakoti, Grace Lin, Emma Anderson, Matt Taylor, Anastasia Ostrowski, Cynthia Breazeal, Eric Klopfer, Hal Abelson

TL;DR

This study addresses the practical challenges of implementing project-based learning (PBL) in K-12 by co-designing large language model (LLM) tools with interdisciplinary teachers. Through two studies combining semi-structured interviews, iterative co-design workshops, and wireframe testing, the authors elicit demands, barriers, and actionable design guidelines for GenAI supports in PBL. They identify three design categories: (A) staging PBL needs, (B) challenges in implementation, and (C) AI integration, culminating in wireframe prototypes for curriculum planning, assessment, and progress tracking. The resulting design guidelines emphasize teacher agency, PD, privacy, blended human-AI workflows, and alignment with the Gold Standard PBL practices, aiming to reduce administrative workload while preserving pedagogical depth. The work advances responsible, teacher-informed deployment of GenAI in PBL and provides a concrete blueprint for future tools and evaluations in real classrooms.

Abstract

The emergence of generative AI, particularly large language models (LLMs), has opened the door for student-centered and active learning methods like project-based learning (PBL). However, PBL poses practical implementation challenges for educators around project design and management, assessment, and balancing student guidance with student autonomy. The following research documents a co-design process with interdisciplinary K-12 teachers to explore and address the current PBL challenges they face. Through teacher-driven interviews, collaborative workshops, and iterative design of wireframes, we gathered evidence for ways LLMs can support teachers in implementing high-quality PBL pedagogy by automating routine tasks and enhancing personalized learning. Teachers in the study advocated for supporting their professional growth and augmenting their current roles without replacing them. They also identified affordances and challenges around classroom integration, including resource requirements and constraints, ethical concerns, and potential immediate and long-term impacts. Drawing on these, we propose design guidelines for future deployment of LLM tools in PBL.

Co-designing Large Language Model Tools for Project-Based Learning with K12 Educators

TL;DR

This study addresses the practical challenges of implementing project-based learning (PBL) in K-12 by co-designing large language model (LLM) tools with interdisciplinary teachers. Through two studies combining semi-structured interviews, iterative co-design workshops, and wireframe testing, the authors elicit demands, barriers, and actionable design guidelines for GenAI supports in PBL. They identify three design categories: (A) staging PBL needs, (B) challenges in implementation, and (C) AI integration, culminating in wireframe prototypes for curriculum planning, assessment, and progress tracking. The resulting design guidelines emphasize teacher agency, PD, privacy, blended human-AI workflows, and alignment with the Gold Standard PBL practices, aiming to reduce administrative workload while preserving pedagogical depth. The work advances responsible, teacher-informed deployment of GenAI in PBL and provides a concrete blueprint for future tools and evaluations in real classrooms.

Abstract

The emergence of generative AI, particularly large language models (LLMs), has opened the door for student-centered and active learning methods like project-based learning (PBL). However, PBL poses practical implementation challenges for educators around project design and management, assessment, and balancing student guidance with student autonomy. The following research documents a co-design process with interdisciplinary K-12 teachers to explore and address the current PBL challenges they face. Through teacher-driven interviews, collaborative workshops, and iterative design of wireframes, we gathered evidence for ways LLMs can support teachers in implementing high-quality PBL pedagogy by automating routine tasks and enhancing personalized learning. Teachers in the study advocated for supporting their professional growth and augmenting their current roles without replacing them. They also identified affordances and challenges around classroom integration, including resource requirements and constraints, ethical concerns, and potential immediate and long-term impacts. Drawing on these, we propose design guidelines for future deployment of LLM tools in PBL.

Paper Structure

This paper contains 46 sections, 14 figures, 3 tables.

Table of Contents

  1. INTRODUCTION
  2. Our Contribution
  3. RELATED WORK
  4. Project-Based Learning
  5. AI Tools to Support PBL Pedagogical Needs
  6. Co-designing Educational Tools with Teachers
  7. METHODS
  8. STUDY 1
  9. Participants and Recruitment
  10. Data Collection
  11. Interviews
  12. Co-design Workshops
  13. Workshop 1
  14. Workshop 2
  15. PBL GenAI Wireframes Walkthrough
  16. ...and 31 more sections

Figures (14)

  • Figure 1: Examples of blank worksheets distributed to participants in workshop 2 outlining stakeholder impacts and ethical implications of PBL-LLM tools
  • Figure 2: A timeline illustrating the various stages of our study alongside the corresponding paper section numbers where their findings are discussed. For Study 2, note that we present findings from the final wireframe testing phase only, as mentioned in Section 3.2.3
  • Figure 3: A figure displaying the mapping of research objectives to the different stages of the study and their results' coded themes
  • Figure 4: Storyboard (P11) mapping a step-by-step teacher-LLM interaction for project and assessment ideation
  • Figure 5: Storyboard (P05) showing an LLM tool for alternative assignments and lesson plans
  • ...and 9 more figures