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…”
BackgroundMethodInfluentialLuger, E., & Sellen, A. (2016) · Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems · doi:10.1145/2858036.2858288 · Cited by 1,176 · cited 1×
“The resulting conversational breakdowns decrease users’ satisfaction, trust, and willingness to continue talking to conversational agents [113, 114, 152].”
BackgroundA Systematic Review of Social Presence: Definition, Antecedents, and Implications
Oh, C. S., Bailenson, J. N., & Welch, G. F. (2018) · Frontiers in Robotics and AI · doi:10.3389/frobt.2018.00114 · Cited by 1,032 · cited 1×
“For conversational agents, social presence is the feeling and perception of interacting with a human being [138], and has been shown to increase the use of conversational agents [134], and can even increase perceived usefulness, trust, and enjoyment [84].”
BackgroundHassanein, K., & Head, M. (2007) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2006.11.018 · Cited by 986 · cited 2×
“We Share success and personalize mistakes [96, 148] S4 Uncertain/Verification Show uncertainty via verification of work [17, 108] S5 Social Presence Actively listen rather than interrupt [41, 64, 84, 134] Technical Skills”
BackgroundThe effectiveness of corrective feedback in SLA: A meta-analysis
Li, S. (2010) · Language Learning · doi:10.1111/j.1467-9922.2010.00561.x · Cited by 941
Effectiveness of Intelligent Tutoring Systems: A Meta-Analytic Review
Kulik, J. A., & Fletcher, J. D. (2016) · Review of Educational Research · doi:10.3102/0034654315581420 · Cited by 930
Intelligent tutoring systems and learning outcomes: A meta-analysis
Ma, W., Adesope, O. O., Nesbit, J. C., & Liu, Q. (2014) · Journal of Educational Psychology · doi:10.1037/a0037123 · Cited by 840 · cited 1×
“ITSs are known to increase student performance well beyond conventional classes [131, 153, 174, 240], and in some cases, outperform human tutoring [230, 231, 239].”
BackgroundBrandtzaeg, P. B., & Følstad, A. (2017) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-70284-1_30 · Cited by 788 · cited 1×
“” Research corroborates this claim, as potential productivity has shown to be a significant motivator for the utilization of conversation agents [34].”
BackgroundThe design and implementation of Xiaoice, an empathetic social chatbot
Zhou, L., Gao, J., Li, D., & Shum, H.-Y. (2020) · Computational Linguistics · doi:10.1162/coli_a_00368 · Cited by 777
The Design and Implementation of XiaoIce, an Empathetic Social Chatbot
Zhou, L., Gao, J., Li, D., & Shum, H.-Y. (2018) · arXiv · doi:10.48550/arxiv.1812.08989 · Cited by 777
Timing of feedback and verbal learning.
Kulik, J. A., & Kulik, C.-L. C. (1988) · Review of Educational Research · doi:10.3102/00346543058001079 · Cited by 703
Towards a Human-like Open-Domain Chatbot
Adiwardana, D., Luong, M.-T., So, D. R., Hall, J., Fiedel, N., Thoppilan, R., Yang, Z., Kulshreshtha, A., Nemade, G., Lu, Y., et al. (2020) · arXiv · doi:10.48550/arxiv.2001.09977 · Cited by 614
Fraser, G., & Arcuri, A. (2013) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2012.14 · Cited by 586 · cited 1×
“Currently, language models such as GPT-3 [37] can be trained from GitHub [37, 95–97] to generate code, while automated test cases can be generated by tools such as Randoop [183] and EvoSuite [81, 82, 203].”
MethodRelational agents: a model and implementation of building user trust
Bickmore, T., & Cassell, J. (2001) · Proceedings of the SIGCHI Conference on Human Factors in Computing Systems · doi:10.1145/365024.365304 · Cited by 479
Sproull, L., Subramani, M., Kiesler, S., Walker, J., & Waters, K. (1996) · Human-Computer Interaction · doi:10.1207/s15327051hci1102_1 · Cited by 399 · cited 4×
“F1 Avatar Embodied by a dynamic 3D avatar [19, 21, 32, 119, 179, 209] F2 Gender Gender can be toggled [26, 38, 184] F3 Voice Communicate via voice synthesis [21, 31, 187] F4 Text Chat Communicate via shared text chat Interaction”
BackgroundMethodInfluentialWhen Are Tutorial Dialogues More Effective Than Reading?
VanLehn, K., Graesser, A. C., Jackson, G. T., Jordan, P., Olney, A., & Rosé, C. P. (2007) · Cognitive Science · doi:10.1080/03640210709336984 · Cited by 378 · cited 1×
“ITSs are known to increase student performance well beyond conventional classes [131, 153, 174, 240], and in some cases, outperform human tutoring [230, 231, 239].”
BackgroundEvaluating and Informing the Design of Chatbots
Jain, M., Kumar, P., Kota, R., & Patel, S. N. (2018) · Proceedings of the 2018 Designing Interactive Systems Conference · doi:10.1145/3196709.3196735 · Cited by 376
Steenbergen-Hu, S., & Cooper, H. (2014) · Journal of Educational Psychology · doi:10.1037/a0034752 · Cited by 355 · cited 1×
“ITSs are known to increase student performance well beyond conventional classes [131, 153, 174, 240], and in some cases, outperform human tutoring [230, 231, 239].”
BackgroundThe effect of social presence and chatbot errors on trust
Toader, D.-C., Boca, G., Toader, R., Măcelaru, M., Toader, C., Ighian, D., & Rădulescu, A. T. (2019) · Sustainability · doi:10.3390/su12010256 · Cited by 233
Resilient Chatbots: Repair Strategy Preferences for Conversational Breakdowns
Ashktorab, Z., Jain, M., Liao, Q. V., & Weisz, J. D. (2019) · Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3290605.3300484 · Cited by 224 · cited 2×
“For example, when a test case fails, PairBuddy will take ownership saying, “I think I made a mistake,” but if all the test cases pass, PairBuddy might say, “Great, we did it!” Research suggests that conversational agents should pre-emptively use uncertainty to avoid situations where they make large miscommunications […”
BackgroundSupportingTrust in Autonomous Driving
Häuslschmid, R., von Bülow, M., Pfleging, B., & Butz, A. (2017) · Proceedings of the 22nd International Conference on Intelligent User Interfaces · doi:10.1145/3025171.3025198 · Cited by 170
Intelligent tutoring systems for programming education: a systematic review
Crow, T., Luxton-Reilly, A., & Wuensche, B. (2018) · Proceedings of the 20th Australasian Computing Education Conference · doi:10.1145/3160489.3160492 · Cited by 166
Personification of the Amazon Alexa: BFF or a Mindless Companion
Lopatovska, I., & Williams, H. (2018) · Proceedings of the 2018 Conference on Human Information Interaction&Retrieval - CHIIR '18 · doi:10.1145/3176349.3176868 · Cited by 160
Open source barriers to entry, revisited: a sociotechnical perspective
Mendez, C., Padala, H. S., Steine-Hanson, Z., Hilderbrand, C., Horvath, A., Hill, C., Simpson, L., Patil, N., Sarma, A., & Burnett, M. (2018) · Proceedings of the 40th International Conference on Software Engineering · doi:10.1145/3180155.3180241 · Cited by 118 · cited 1×
“We purposefully achieved a gender balance since research has shown a difference in preference and behavior across various genders [39, 48, 87, 160, 166, 215].”
BackgroundFarmChat: A Conversational Agent to Answer Farmer Queries
Jain, M., Kumar, P., Bhansali, I., Liao, Q. V., Truong, K., & Patel, S. (2018) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3287048 · Cited by 117
Wargnier, P., Carletti, G., Laurent-Corniquet, Y., Benveniste, S., Jouvelot, P., & Rigaud, A.-S. (2016) · 2016 IEEE International Conference on Serious Games and Applications for Health (SeGAH) · doi:10.1109/segah.2016.7586282 · Cited by 28 · cited 1×
“It helps develop user-friendly interfaces that promote natural language dialogue, consider the unique qualities of human-agent interaction as distinct from normal human discourse [59], and study user interactions with conversational agents [29, 32, 252].”
BackgroundA principled evaluation for a principled idea garden
Jernigan, W., Horvath, A., Lee, M., Burnett, M., Cuilty, T., Kuttal, S., Peters, A., Kwan, I., Bahmani, F., & Ko, A. (2015) · 2015 IEEE Symposium on Visual Languages and Human-Centric Computing (VL/HCC) · doi:10.1109/vlhcc.2015.7357222 · Cited by 28
Self-citationKuttal, S. K., Myers, J., Gurka, S., Magar, D., Piorkowski, D., & Bellamy, R. (2020) · 2020 IEEE Symposium on Visual Languages and Human-Centric Computing (VL/HCC) · doi:10.1109/vl/hcc50065.2020.9127276 · Cited by 27 · cited 3×
“Lack of Support for Creativity: As identified in previous research [134], programmers follow the Osborn–Parnes Creative Problem Solving Process when working together.”
BackgroundMethodSelf-citation
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.