Towards Human-Bot Collaborative Software Architecting with ChatGPT
Open accessThe DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.
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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The authors also uncovered ChatGPT’s capacity to identify and address ethical, governance, and socio-technical considerations within this context66.”
From On opportunities and challenges of large multimodal foundation models in education (2025) · cites this paper as [66]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“This has resulted in a number of recent studies that investigate the impact of technology on design and creative workflows, and the potential for its usage as a design support tool (e.g.[2,11,20,24,58]).”
From Is Resistance Futile?: Early Career Game Developers, Generative AI, and Ethical Skepticism (2024) · cites this paper as [2]
In the citing paper
“An initial case study within this domain explored the potential synergies between ChatGPT and architects’ decision-making, aiming to automate various facets of ACSE, as documented by Ahmad66.”
From On opportunities and challenges of large multimodal foundation models in education (2025) · cites this paper as [66]
In the citing paper
“A notable example of collaborative programming involves the concept of Human-Bot Collaborative Architecting, with a specific emphasis on the integration of ChatGPT into human decision-making processes to streamline aspects of Architecture-Centric Software Engineering (ACSE).”
From On opportunities and challenges of large multimodal foundation models in education (2025) · cites this paper as [66]
In the citing paper
“Consistency and ethics: Studies on Architecture-Centric Software Engineering (ACSE) using ChatGPT highlight several concerns66.”
From On opportunities and challenges of large multimodal foundation models in education (2025) · cites this paper as [66]
2 more claims about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
A survey on software architecture analysis methods
Dobrica, L., & Niemela, E. (2002) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2002.1019479 · Cited by 518 · cited 8×
“To design and conduct this study, and considering the internal validity, we followed a systematic approach and utilized a well-known architecting process [9] and architecture evaluation method [6].”
BackgroundMethodInfluentialA Categorical Archive of ChatGPT Failures
Borji, A. (2023) · arXiv · doi:10.48550/arxiv.2302.03494 · Cited by 514 · cited 1×
“However, it remains an unexplored territory in terms of its potential and perils in the context of software development processes [17], [18].”
BackgroundAn empirical evaluation of GitHub copilot's code suggestions
Nguyen, N., & Nadi, S. (2022) · Proceedings of the 19th International Conference on Mining Software Repositories · doi:10.1145/3524842.3528470 · Cited by 313 · cited 3×
“Software Development Bots (DevBots) represent conversational agents or recommender systems, driven by AI, to assist software engineers by offering certain degree of automation and/or inducing intelligence in software engineering process [14, 15].”
BackgroundMethodA general model of software architecture design derived from five industrial approaches
Hofmeister, C., Kruchten, P., Nord, R. L., Obbink, H., Ran, A., & America, P. (2007) · Journal of Systems and Software · doi:10.1016/j.jss.2006.05.024 · Cited by 307
What Industry Needs from Architectural Languages: A Survey
Malavolta, I., Lago, P., Muccini, H., Pelliccione, P., & Tang, A. (2013) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2012.74 · Cited by 296 · cited 3×
“The ASRs are synthesized into an architectural model that can be expressed with an architectural (modeling) language, like UML or other architectural languages [14].”
BackgroundMethodInfluentialThe Past, Present, and Future for Software Architecture
Kruchten, P., Obbink, H., & Stafford, J. (2006) · IEEE Software · doi:10.1109/ms.2006.59 · Cited by 231
Applications of AI in classical software engineering
Barenkamp, M., Rebstadt, J., & Thomas, O. (2020) · AI Perspectives · doi:10.1186/s42467-020-00005-4 · Cited by 123 · cited 3×
“The research on synergizing AI and SE can be classified into two distinct dimensions namely AI for SE (artificial intelligence in software engineering) and SE for AI (software engineering for artificial intelligence) [5] [6].”
BackgroundSoftware Architecture in a Changing World
Woods, E. (2016) · IEEE Software · doi:10.1109/ms.2016.149 · Cited by 93 · cited 1×
“Specifically, SE solutions need to maintain the so-called ‘intelligence equilibrium’ – i.e., unifying and balancing machine intelligence and human intellect – in processes, patterns, and tools etc. for emergent classes of software, such as blockchain and quantum applications [16].”
BackgroundCollaborative Modeling and Group Decision Making Using Chatbots in Social Networks
Perez-Soler, S., Guerra, E., & de Lara, J. (2018) · IEEE Software · doi:10.1109/ms.2018.290101511 · Cited by 76 · cited 2×
“[14] (investigating Github Copilot) and a tool (Chatbot named SOCIO) developed by Pérez-Soler et al.[15] highlight the growing impacts and emerging challenges of using bots in software modeling and programming.”
BackgroundMethodAn Analysis of the Automatic Bug Fixing Performance of ChatGPT
(2023) · doi:10.48550/arxiv.2301.08653 · Cited by 49 · cited 6×
“ChatGPT is not specifically developed to address software engineering challenges, however; it is well capable of generating versatile textual specifications including architectural requirements, Unified Modeling Language (UML) scripts, source code libraries, and test cases [11, 17].”
BackgroundMethodInfluential
Research works printed but not linked: 5
- Anonymous. 2023. Replication Package: Towards Human-Bot Collaborative Software Architecting with ChatGPT. In https://anonymous.4open.science/r/ChatGPT4SA-2B61.
- Laurent Avila-Chauvet, Diana Mejía, and Christian Oswaldo Acosta Quiroz. 2023. ChatGPT as a Support Tool for Online Behavioral Task Programming. SSRN preprint SSRN:4329020 (2023).
- Sebastian Herold, Christoph Knieke, Mirco Schindler, and Andreas Rausch. 2020. Towards Improving Software Architecture Degradation Mitigation by Machine Learning. In Proceedings of the 12th International Conference on Adaptive and Self-Adaptive Systems and Applications (ADAPTIVE). IARIA, 36–39.
- Sajed Jalil, Suzzana Rafi, Thomas D LaToza, Kevin Moran, and Wing Lam. 2023. ChatGPT and Software Testing Education: Promises & Perils. arXiv preprint arXiv:2302.03287 (2023). · arXiv
- Junaid Qadir. 2022. Engineering Education in the Era of ChatGPT: Promise and Pitfalls of Generative AI for Education. TechRxiv preprint techrxiv.21789434 (2022).
Cited by
Summary of ChatGPT-Related Research and Perspective Towards the Future of Large Language Models
Liu, Y., Han, T., Ma, S., Zhang, J., Yang, Y., Tian, J., He, H., Li, A., He, M., Liu, Z., et al. (2023) · arXiv · doi:10.48550/arxiv.2304.01852 · Cited by 1,172
Summary of ChatGPT-Related research and perspective towards the future of large language models
Liu, Y., Han, T., Ma, S., Zhang, J., Yang, Y., Tian, J., He, H., Li, A., He, M., Liu, Z., et al. (2023) · Meta-Radiology · doi:10.1016/j.metrad.2023.100017 · Cited by 855
“Ahmad et al. [1] proposed a method for human-machine collaboration using ChatGPT to create software architecture.”
MethodLarge language models for software engineering: survey and open problems
Fan, A., Gokkaya, B., Harman, M., Lyubarskiy, M., Sengupta, S., Yoo, S., & Zhang, J. M. (2023) · 2023 IEEE/ACM International Conference on Software Engineering: Future of Software Engineering (ICSE-FoSE) · doi:10.1109/icse-fose59343.2023.00008 · Cited by 650
“Ahmad et al. [202] explore the way in which a novice software architect could interact with ChatGPT.”
BackgroundUnlocking the opportunities through ChatGPT Tool towards ameliorating the education system
Javaid, M., Haleem, A., Singh, R. P., Khan, S., & Khan, I. H. (2023) · BenchCouncil Transactions on Benchmarks, Standards and Evaluations · doi:10.1016/j.tbench.2023.100115 · Cited by 535
Large Language Models for Software Engineering: Survey and Open Problems
Fan, A., Gokkaya, B., Harman, M., Lyubarskiy, M., Sengupta, S., Yoo, S., & Zhang, J. M. (2023) · arXiv · doi:10.48550/arxiv.2310.03533 · Cited by 523
“Ahmad et al. [202] explore the way in which a novice software architect could interact with ChatGPT.”
Background
Metadata
- Authors
- Ahmad, A., Waseem, M., Liang, P., Fahmideh, M., Aktar, M. S., & Mikkonen, T.
- Affiliations
- Lancaster University (GB)
- University of Jyväskylä (FI)
- Wuhan University (CN)
- University of Southern Queensland (AU)
- Venue
- Proceedings of the 27th International Conference on Evaluation and Assessment in Software Engineering
- Publisher
- ACM
- Published
- 2023-06-14
- Pages
- 279-285
- OpenAlex
- W4380568688
- Cited by
- 168
- References
- 12
- Citations by year
- 2026: 21 · 2025: 55 · 2024: 61 · 2023: 31
- FWCI
- 29.82
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- International Conference on Evaluation and Assessment in Software Engineering (EASE) (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion, cc-by)
- Lancaster EPrints (Lancaster University) (submittedVersion)
- Jyväskylä University Digital Archive (University of Jyväskylä) (submittedVersion, cc-by)
- arXiv (Cornell University) (cc-by)
- Funders
- National Natural Science Foundation of China (62172311)
- Jyväskylän Yliopisto
- Topics
- Physical Sciences › Computer Science › Software › Advanced Software Engineering Methodologies
- Physical Sciences › Computer Science › Information Systems › Software Engineering Techniques and Practices
- Physical Sciences › Computer Science › Information Systems › Software Engineering Research
- Keywords
- software architecture, ChatGPT, large language models, AI decision support
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Towards Human-Bot Collaborative Software Architecting with ChatGPT. https://app.cochat.ai/papers/10.1145/3593434.3593468
- The paper
- Ahmad, A., Waseem, M., Liang, P., Fahmideh, M., Aktar, M. S., & Mikkonen, T. (2023). Towards Human-Bot Collaborative Software Architecting with ChatGPT. Proceedings of the 27th International Conference on Evaluation and Assessment in Software Engineering. https://doi.org/10.1145/3593434.3593468
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.