QBrain: AI-Driven System for Automated Software Quality Assurance
Supervisor Name
Mohammed Khalil
Supervisor Email
m.khalil@ptuk.edu.ps
University
Palestine Technical University - Kadoorie
Research field
Computer Science – Software Engineering and Artificial Intelligence
Bio
Dr. Mohamed Khalil is a faculty member in the Computer Engineering Department, with research focused on Artificial Intelligence (AI) and Machine Learning (ML). His interests include chatbots, intelligent software systems, software engineering, Data Science, Natural Language Processing (NLP), and Computer Vision, with several research publications in these areas.
Description
QBrain is an AI-powered system designed to automate the analysis of Software Requirements Specification (SRS) documents and support the Software Quality Assurance (QA) process by automatically generating software features and test cases. The system processes SRS documents through a multi-stage AI pipeline where users upload SRS files in PDF or TXT format, and the system extracts the textual content using document processing tools such as Google Document AI or PDF parsing utilities. The extracted text is then divided into smaller semantic chunks to enable efficient processing of large documents. For each chunk, the system generates semantic embeddings using an OpenAI embedding model, and these embeddings are stored in a vector database (Supabase pgvector) to enable semantic search and contextual retrieval from the document. Using a Retrieval-Augmented Generation (RAG) architecture implemented with LangChain, the system retrieves the most relevant sections of the SRS and uses them as context for AI generation. Based on this contextual information, QBrain automatically generates structured software features and test cases, including preconditions, testing steps, expected results, and priorities. The platform allows users to review, modify, approve, or delete the AI-generated outputs to ensure accuracy and maintain human oversight in the QA workflow. In addition to AI-based requirement analysis, QBrain provides an integrated environment for managing software testing activities, including project management, feature management, manual and AI-generated test cases, automatic conversion of test cases into Gherkin syntax for Behavior-Driven Development (BDD), bug tracking and reporting, and AI-powered question answering over SRS documents through a chatbot interface. The system also provides an interactive web interface built with React and TypeScript, enabling users to efficiently interact with the platform and manage their testing workflows. This approach significantly reduces the time required for manual SRS analysis, improves traceability between requirements and test artifacts, and enhances the overall efficiency and productivity of QA workflows.
