Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

ROOT: Requirements Organization and Optimization Tool

Katherine R. Dearstyne, Alberto D. Rodriguez, Jane Cleland-Huang

TL;DR

ROOT addresses the burden of requirements management by centralizing project data and enabling AI-assisted documentation, traceability, and collaboration. The approach combines a three-component architecture (FEND/BEND/GEN) with AI-assisted features that leverage Retrieval-Augmented Generation, Chain-of-Thought, and ReAct paradigms. Key contributions include automatic project and artifact summaries, hierarchical documentation generation, predicted trace-links with explanations, and vocabulary health checks, particularly aiding startups and small teams. The work demonstrates practical impact by reducing manual effort and enabling early error detection within integrated knowledge sources like GitHub and Jira.

Abstract

Software engineering practices such as constructing requirements and establishing traceability help ensure systems are safe, reliable, and maintainable. However, they can be resource-intensive and are frequently underutilized. To alleviate the burden of these essential processes, we developed the Requirements Organization and Optimization Tool (ROOT). ROOT centralizes project information and offers project visualizations and AI-based tools designed to streamline engineering processes. With ROOT's assistance, engineers benefit from improved oversight and early error detection, leading to the successful development of software systems. Link to screen cast: https://youtu.be/3rtMYRnsu24

ROOT: Requirements Organization and Optimization Tool

TL;DR

ROOT addresses the burden of requirements management by centralizing project data and enabling AI-assisted documentation, traceability, and collaboration. The approach combines a three-component architecture (FEND/BEND/GEN) with AI-assisted features that leverage Retrieval-Augmented Generation, Chain-of-Thought, and ReAct paradigms. Key contributions include automatic project and artifact summaries, hierarchical documentation generation, predicted trace-links with explanations, and vocabulary health checks, particularly aiding startups and small teams. The work demonstrates practical impact by reducing manual effort and enabling early error detection within integrated knowledge sources like GitHub and Jira.

Abstract

Software engineering practices such as constructing requirements and establishing traceability help ensure systems are safe, reliable, and maintainable. However, they can be resource-intensive and are frequently underutilized. To alleviate the burden of these essential processes, we developed the Requirements Organization and Optimization Tool (ROOT). ROOT centralizes project information and offers project visualizations and AI-based tools designed to streamline engineering processes. With ROOT's assistance, engineers benefit from improved oversight and early error detection, leading to the successful development of software systems. Link to screen cast: https://youtu.be/3rtMYRnsu24
Paper Structure (18 sections, 8 figures)

This paper contains 18 sections, 8 figures.

Table of Contents

  1. Introduction
  2. Related Work
  3. Architecture and Processes
  4. Architecture
  5. Job-Execution
  6. AI-based Features
  7. Walk Through
  8. On-boarding:
  9. Integration Across Knowledge Sources
  10. Project Summarization
  11. Artifact Generation
  12. Project Visualization
  13. AI-based Project Chat:
  14. Trace-link Generation:
  15. Project Vocabulary:
  16. ...and 3 more sections

Figures (8)

  • Figure 1: Slice of documentation and links generated for Autoware Autowarefoundation open source project.
  • Figure 2: Project overview screen containing Traceability Information Model (TIM) and graph controls. Project summary excluded for display purposes.
  • Figure 3: Selected artifact view of generated feature containing description and further details.
  • Figure 4: Tree view of generated feature from Autoware Project.
  • Figure 5: Table view of search results for query 'braking'.
  • ...and 3 more figures