Degree

Master of Science in Management

School

School of Business Studies (SBS)

Department

Department of Management

Date of Submission

Summer 2026-9-7

Supervisor

Dr. Abdul Basad Shaikh, Assistant Professor, Institute of Business Administration, Karachi

Submission Type

MS Management Research Project

Document Type

Restricted Access

Keywords

Prompt Design, Large Language Models, Digital Literacy

Abstract

With an increasing number of Large Language Models (LLMs) like ChatGPT, there are huge opportunities for using digital literacy learning in under-resourced communities. But their usefulness to adults with low literacy rates and who don't speak English has barely been explored in the literature. This study aims to fill that gap by examining the impact of four evidence-based prompt design approaches (scaffolding, Socratic, role-based, and reflective) on the reflective engagement and accessibility of Urdu speaking, matric or intermediate pass, Pakistani working-class adult participants when engaging with ChatGPT in a researcher-facilitated session focused on a real-life digital safety scenario. The study uses a qualitative, exploratory, design-based research approach with a purposively selected sample of 10 participants, inspired by the AI-as-collaborator paradigm as described by Ouyang and Jiao (2021), Problem-Based Learning by Barrows and Tamblyn (1980), and Sharma and Khadka's (2026) operationalisation of Cognitive Load Theory (CLT). The data is gathered from three sources: transcripts of the conversations with ChatGPT, oral reflection interviews after each session, and observation notes of the researchers. Thematic analysis is done using the 6 phases outlined by Braun and Clarke (2006). This study aims to develop a set of 4-6 empirically grounded Urdu prompt design principles that can be applied to future AI-mediated learning interventions for non-formally educated adult populations in Pakistan and similar low-resource settings.

The full text of this document is only accessible to authorized users.

Share

COinS