View Proposal
-
Proposer
-
Andrew Ireland
-
Title
-
A Smart Requirements Writing Assistant
-
Goal
-
Build a Use Case Assistant
-
Description
- Most requirement specifications are written in natural language (NL). NL documents are inherently imprecise. EARS is a pattern-based method for constraining the formulation of NL requirements. The goal of this project is to develop a tool that implement the EARS method. In addition, the tool will include 'automated critic', i.e., it will access a LLM (e.g., Google Gemini) to provide suggestions about requirements provided by a user, e.g., possible failure modes that could be added, refinements within the context of conditional requirements.
- Resources
-
Appropriate programming languages, i.e., ideally a language that provides an API to a LLM.
-
Background
-
Software Design
-
Url
-
External Link
-
Difficulty Level
-
Challenging
-
Ethical Approval
-
None
-
Number Of Students
-
1
-
Supervisor
-
Andrew Ireland
-
Keywords
-
-
Degrees
-
Bachelor of Science in Computer Science
Master of Engineering in Software Engineering
Master of Science in Software Engineering