Primary supervisor

Chetan Arora

This project focuses specifically on LLM applications: chatbots used in customer support (e.g., healthcare). The goal is to investigate how user requirements (e.g., “the bot should de-escalate frustrated users”) can be systematically translated into prompt templates or prompt strategies.

Instead of treating prompt engineering as a trial-and-error process, this project will explore how RE principles, like functional requirements and acceptance criteria, can be mapped to prompt artifacts. The project will evaluate prompt variants and trace their effectiveness in meeting specified requirements using defined metrics (e.g., user satisfaction, task completion rate, tone control).

Keywords: Software Engineering, LLM-based systems, Prompt Engineering, Requirements Analysis.

Student cohort

Single Semester
Double Semester

Aim/outline

  1. To identify and formalise functional and non-functional requirements for LLM-based chatbots.
  2. To develop a systematic approach for translating requirements into structured prompt templates or prompt strategies.
  3. To implement and compare different prompt variants and strategies.
  4. To evaluate how well each prompt variant satisfies the original requirements using defined metrics.

Required knowledge

- The students should be experienced in Python programming.

- An understanding of functional and non-functional requirements and prompting strategies is preferred.