Unveiling the Potential of a Conversational Agent in Developer Support: Insights from Mozilla's PDF.js Project

João Correia, Morgan C. Nicholson, Daniel Coutinho, Caio Barbosa, Marco Castelluccio, Marco Gerosa, Alessandro Garcia, Igor Steinmacher

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Large language models and other foundation models (FMs) boost productivity by automating code generation, supporting bug fixes, and generating documentation. We propose that FMs can further support Open Source Software (OSS) projects by assisting developers and guiding the community. Currently, core developers and maintainers answer queries about processes, architecture, and source code, but their time is limited, often leading to delays. To address this, we introduce DevMentorAI, a tool that enhances developer-project interactions by leveraging source code and technical documentation. DevMentorAI uses the Retrieval Augmented Generation (RAG) architecture to identify and retrieve relevant content for queries. We evaluated DevMentorAI with a case study on PDF.js project, using real questions from a development chat room and comparing the answers provided by DevMentorAI to those from humans. A Mozilla expert rated the answers, finding DevMentorAI's responses more satisfactory in 8/14 of cases, equally satisfactory in 3/14, and less satisfactory in 3/14. These results demonstrate the potential of using foundation models and the RAG approach to support developers and reduce the burden on core developers.

Original languageEnglish (US)
Title of host publicationAIware 2024 - Proceedings of the 1st ACM International Conference on AI-Powered Software, Co-located with
Subtitle of host publicationESEC/FSE 2024
EditorsBram Adams, Thomas Zimmermann, Ipek Ozkaya, Dayi Lin, Jie M. Zhang
PublisherAssociation for Computing Machinery, Inc
Pages10-18
Number of pages9
ISBN (Electronic)9798400706851
DOIs
StatePublished - Jul 10 2024
Event1st ACM International Conference on AI-Powered Software, AIware 2024, co-located with the ACM International Conference on the Foundations of Software Engineering, FSE 2024 - Porto de Galinhas, Brazil
Duration: Jul 15 2024Jul 16 2024

Publication series

NameAIware 2024 - Proceedings of the 1st ACM International Conference on AI-Powered Software, Co-located with: ESEC/FSE 2024

Conference

Conference1st ACM International Conference on AI-Powered Software, AIware 2024, co-located with the ACM International Conference on the Foundations of Software Engineering, FSE 2024
Country/TerritoryBrazil
CityPorto de Galinhas
Period7/15/247/16/24

Keywords

  • Conversational Agents
  • Developer Assistance
  • Large Language Models
  • Software Development
  • Software Engineering

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Unveiling the Potential of a Conversational Agent in Developer Support: Insights from Mozilla's PDF.js Project'. Together they form a unique fingerprint.

Cite this