Teacher-AI Collaboration for Curating and Customizing Lesson Plans in Low-Resource Schools

2025-07-01

AI Summary

This study addresses the challenges of scarce resources, multilingual instruction, and excessive lesson-planning burdens hindering activity-based pedagogy in government schools across Karnataka, India. We propose and empirically evaluate Shiksha Copilot—an AI-augmented tool that integrates large language models (LLMs) with educator expertise through a two-tier human-AI co-design workflow: curriculum designers collaborate with AI to generate foundational lesson plans, which frontline teachers then localize into bilingual (English-Kannada) activity-based lesson plans. A large-scale mixed-methods evaluation demonstrates significant reductions in teacher preparation time, administrative load, and instructional stress, alongside marked increases in activity-oriented teaching practice. The study contributes robust empirical evidence for the feasibility and effectiveness of structured, tiered human-AI collaboration in low-resource, multilingual educational contexts, thereby advancing a “teacher-centered” design paradigm for educational AI.

Technology Category

• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

This study investigates Shiksha copilot, an AI-assisted lesson planning tool deployed in government schools across Karnataka, India. The system combined LLMs and human expertise through a structured process in which English and Kannada lesson plans were co-created by curators and AI; teachers then further customized these curated plans for their classrooms using their own expertise alongside AI support. Drawing on a large-scale mixed-methods study involving 1,043 teachers and 23 curators, we examine how educators collaborate with AI to generate context-sensitive lesson plans, assess the quality of AI-generated content, and analyze shifts in teaching practices within multilingual, low-resource environments. Our findings show that teachers used Shiksha copilot both to meet administrative documentation needs and to support their teaching. The tool eased bureaucratic workload, reduced lesson planning time, and lowered teaching-related stress, while promoting a shift toward activity-based pedagogy. However, systemic challenges such as staffing shortages and administrative demands constrained broader pedagogical change. We frame these findings through the lenses of teacher-AI collaboration and communities of practice to examine the effective integration of AI tools in teaching. Finally, we propose design directions for future teacher-centered EdTech, particularly in multilingual and Global South contexts.

Problem

• AI-human collaboration for lesson planning in low-resource schools
• Assessing quality and impact of AI-generated educational content
• Addressing systemic challenges in teacher-AI EdTech integration

Innovation

• AI-human co-creation of lesson plans
• Multilingual LLM support for low-resource schools
• Teacher-AI collaboration reduces planning time