Home > Research > Publications & Outputs > Towards Human-Bot Collaborative Software Archit...

Electronic data

  • EASE-23

    Accepted author manuscript, 1.73 MB, PDF document

    Available under license: CC BY: Creative Commons Attribution 4.0 International License

Links

Text available via DOI:

View graph of relations

Towards Human-Bot Collaborative Software Architecting with ChatGPT

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published

Standard

Towards Human-Bot Collaborative Software Architecting with ChatGPT. / Ahmad, Aakash; Waseem, Muhammad; Liang, Peng et al.
Proceedings of EASE 2023 - Evaluation and Assessment in Software Engineering. New York: ACM, 2023. p. 279-285 (ACM International Conference Proceeding Series).

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Harvard

Ahmad, A, Waseem, M, Liang, P, Fahmideh, M, Aktar, MS & Mikkonen, T 2023, Towards Human-Bot Collaborative Software Architecting with ChatGPT. in Proceedings of EASE 2023 - Evaluation and Assessment in Software Engineering. ACM International Conference Proceeding Series, ACM, New York, pp. 279-285. https://doi.org/10.1145/3593434.3593468

APA

Ahmad, A., Waseem, M., Liang, P., Fahmideh, M., Aktar, M. S., & Mikkonen, T. (2023). Towards Human-Bot Collaborative Software Architecting with ChatGPT. In Proceedings of EASE 2023 - Evaluation and Assessment in Software Engineering (pp. 279-285). (ACM International Conference Proceeding Series). ACM. https://doi.org/10.1145/3593434.3593468

Vancouver

Ahmad A, Waseem M, Liang P, Fahmideh M, Aktar MS, Mikkonen T. Towards Human-Bot Collaborative Software Architecting with ChatGPT. In Proceedings of EASE 2023 - Evaluation and Assessment in Software Engineering. New York: ACM. 2023. p. 279-285. (ACM International Conference Proceeding Series). Epub 2023 Jun 14. doi: 10.1145/3593434.3593468

Author

Ahmad, Aakash ; Waseem, Muhammad ; Liang, Peng et al. / Towards Human-Bot Collaborative Software Architecting with ChatGPT. Proceedings of EASE 2023 - Evaluation and Assessment in Software Engineering. New York : ACM, 2023. pp. 279-285 (ACM International Conference Proceeding Series).

Bibtex

@inproceedings{654ce580f04c46cea8f0575bd668c37e,
title = "Towards Human-Bot Collaborative Software Architecting with ChatGPT",
abstract = "Architecting software-intensive systems can be a complex process. It deals with the daunting tasks of unifying stakeholders' perspectives, designers' intellect, tool-based automation, pattern-driven reuse, and so on, to sketch a blueprint that guides software implementation and evaluation. Despite its benefits, architecture-centric software engineering (ACSE) suffers from a multitude of challenges. ACSE challenges could stem from a lack of standardized processes, socio-technical limitations, and scarcity of human expertise etc. that can impede the development of existing and emergent classes of software. Software Development Bots (DevBots) trained on large language models can help synergise architects' knowledge with artificially intelligent decision support to enable rapid architecting in a human-bot collaborative ACSE. An emerging solution to enable this collaboration is ChatGPT, a disruptive technology not primarily introduced for software engineering, but is capable of articulating and refining architectural artifacts based on natural language processing. We detail a case study that involves collaboration between a novice software architect and ChatGPT to architect a service-based software. Future research focuses on harnessing empirical evidence about architects' productivity and explores socio-technical aspects of architecting with ChatGPT to tackle challenges of ACSE.",
keywords = "ChatGPT, DevBots, Large Language Models, Software Architecture",
author = "Aakash Ahmad and Muhammad Waseem and Peng Liang and Mahdi Fahmideh and Aktar, {Mst Shamima} and Tommi Mikkonen",
year = "2023",
month = jun,
day = "14",
doi = "10.1145/3593434.3593468",
language = "English",
series = "ACM International Conference Proceeding Series",
publisher = "ACM",
pages = "279--285",
booktitle = "Proceedings of EASE 2023 - Evaluation and Assessment in Software Engineering",

}

RIS

TY - GEN

T1 - Towards Human-Bot Collaborative Software Architecting with ChatGPT

AU - Ahmad, Aakash

AU - Waseem, Muhammad

AU - Liang, Peng

AU - Fahmideh, Mahdi

AU - Aktar, Mst Shamima

AU - Mikkonen, Tommi

PY - 2023/6/14

Y1 - 2023/6/14

N2 - Architecting software-intensive systems can be a complex process. It deals with the daunting tasks of unifying stakeholders' perspectives, designers' intellect, tool-based automation, pattern-driven reuse, and so on, to sketch a blueprint that guides software implementation and evaluation. Despite its benefits, architecture-centric software engineering (ACSE) suffers from a multitude of challenges. ACSE challenges could stem from a lack of standardized processes, socio-technical limitations, and scarcity of human expertise etc. that can impede the development of existing and emergent classes of software. Software Development Bots (DevBots) trained on large language models can help synergise architects' knowledge with artificially intelligent decision support to enable rapid architecting in a human-bot collaborative ACSE. An emerging solution to enable this collaboration is ChatGPT, a disruptive technology not primarily introduced for software engineering, but is capable of articulating and refining architectural artifacts based on natural language processing. We detail a case study that involves collaboration between a novice software architect and ChatGPT to architect a service-based software. Future research focuses on harnessing empirical evidence about architects' productivity and explores socio-technical aspects of architecting with ChatGPT to tackle challenges of ACSE.

AB - Architecting software-intensive systems can be a complex process. It deals with the daunting tasks of unifying stakeholders' perspectives, designers' intellect, tool-based automation, pattern-driven reuse, and so on, to sketch a blueprint that guides software implementation and evaluation. Despite its benefits, architecture-centric software engineering (ACSE) suffers from a multitude of challenges. ACSE challenges could stem from a lack of standardized processes, socio-technical limitations, and scarcity of human expertise etc. that can impede the development of existing and emergent classes of software. Software Development Bots (DevBots) trained on large language models can help synergise architects' knowledge with artificially intelligent decision support to enable rapid architecting in a human-bot collaborative ACSE. An emerging solution to enable this collaboration is ChatGPT, a disruptive technology not primarily introduced for software engineering, but is capable of articulating and refining architectural artifacts based on natural language processing. We detail a case study that involves collaboration between a novice software architect and ChatGPT to architect a service-based software. Future research focuses on harnessing empirical evidence about architects' productivity and explores socio-technical aspects of architecting with ChatGPT to tackle challenges of ACSE.

KW - ChatGPT

KW - DevBots

KW - Large Language Models

KW - Software Architecture

U2 - 10.1145/3593434.3593468

DO - 10.1145/3593434.3593468

M3 - Conference contribution/Paper

T3 - ACM International Conference Proceeding Series

SP - 279

EP - 285

BT - Proceedings of EASE 2023 - Evaluation and Assessment in Software Engineering

PB - ACM

CY - New York

ER -