Designing PairBuddy—A Conversational Agent for Pair Programming
The DOI matches its Crossref record; 37 of the 37 references it cites were found in a registry or an index.
Abstract
From automated customer support to virtual assistants, conversational agents have transformed everyday interactions, yet despite phenomenal progress, no agent exists for programming tasks. To understand the design space of such an agent, we prototyped PairBuddy—an interactive pair programming partner—based on research from conversational agents, software engineering, education, human-robot interactions, psychology, and artificial intelligence. We iterated PairBuddy’s design using a series of Wizard-of-Oz studies. Our pilot study of six programmers showed promising results and provided insights toward PairBuddy’s interface design. Our second study of 14 programmers was positively praised across all skill levels. PairBuddy’s active application of soft skills—adaptability, motivation, and social presence—as a navigator increased participants’ confidence and trust, while its technical skills—code contributions, just-in-time feedback, and creativity support—as a driver helped participants realize their own solutions. PairBuddy takes the first step towards an Alexa-like programming partner.
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.
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
Using thematic analysis in psychology
Braun, V., & Clarke, V. (2006) · Qualitative Research in Psychology · doi:10.1191/1478088706qp063oa · Cited by 194,414
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
Hattie, J., & Timperley, H. (2007) · Review of Educational Research · doi:10.3102/003465430298487 · Cited by 12,905
Likert Scale: Explored and Explained
Joshi, A., Kale, S., Chandel, S., & Pal, D. (2015) · British Journal of Applied Science & Technology · doi:10.9734/bjast/2015/14975 · Cited by 3,870
Self-Determination Theory in Work Organizations: The State of a Science
Deci, E. L., Olafsen, A. H., & Ryan, R. M. (2017) · Annual Review of Organizational Psychology and Organizational Behavior · doi:10.1146/annurev-orgpsych-032516-113108 · Cited by 3,199
Guidelines for Human-AI Interaction
Amershi, S., Weld, D., Vorvoreanu, M., Fourney, A., Nushi, B., Collisson, P., Suh, J., Iqbal, S., Bennett, P. N., Inkpen, K., et al. (2019) · Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3290605.3300233 · Cited by 2,439 · cited 9×
“Therefore, we formulated design decision I2: PairBuddy will provide timed feedback [14].”
BackgroundMethodInfluentialMethods of coping with social desirability bias: A review
Nederhof, A. J. (1985) · European Journal of Social Psychology · doi:10.1002/ejsp.2420150303 · Cited by 2,340 · cited 1×
“To avoid social desirability bias [94, 173], we told participants that the study was being used to improve PairBuddy’s design and that honest feedback was crucial to evaluate our system.”
MethodVanLEHN, K. (2011) · Educational Psychologist · doi:10.1080/00461520.2011.611369 · Cited by 2,323
Intrinsic motivation and extrinsic incentives jointly predict performance: A 40-year meta-analysis.
Cerasoli, C. P., Nicklin, J. M., & Ford, M. T. (2014) · Psychological Bulletin · doi:10.1037/a0035661 · Cited by 1,981 · cited 3×
“Motivation is seen as a driving force that has a substantial impact on a programmer’s performance and productivity [13, 34], and comes from either intrinsic or extrinsic sources [34, 49].”
BackgroundAmabile, T. M., & Pratt, M. G. (2016) · Research in Organizational Behavior · doi:10.1016/j.riob.2016.10.001 · Cited by 1,863 · cited 5×
“ID Design Decision Description Example Sources Interface F1 Avatar Embodied by a 3D lip-synced avatar [25, 28, 43, 151, 229, 270] F2 Gender Gender can be toggled [33, 50, 236] F3 Voice Communicate via voice synthesis [28, 41, 242] F4 Text Chat Paste images or links Interactions I1 Direct Driving Edit code via IDE I2 A…”
BackgroundMethodInfluential
Cited by
Ross, S. I., Martinez, F., Houde, S., Muller, M., & Weisz, J. D. (2023) · Proceedings of the 28th International Conference on Intelligent User Interfaces · doi:10.1145/3581641.3584037 · Cited by 258
Using AI-based coding assistants in practice: State of affairs, perceptions, and ways forward
Sergeyuk, A., Golubev, Y., Bryksin, T., & Ahmed, I. (2025) · Information and Software Technology · doi:10.1016/j.infsof.2024.107610 · Cited by 101
Zhu, M., & Zhang, K. (2025) · Technology, Knowledge and Learning · doi:10.1007/s10758-025-09859-1 · Cited by 13
Metadata
- Authors
- Robe, P., & Kuttal, S. K.
- Venue
- ACM Transactions on Computer-Human Interaction
- Published
- 2022-05-05
- Volume
- 29
- Issue
- 4
- Pages
- 1-44
- ISSN
- 1073-0516 (ISSN-L)
- 1557-7325
- OpenAlex
- W4229050671
- Cited by
- 44
- References
- 37
- FWCI
- 7.80
- Type
- journal article
- Language
- en
- Open access
- closed
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
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.