Towards More Effective AI-Assisted Programming: A Systematic Design Exploration to Improve Visual Studio IntelliCode’s User Experience
The DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.
Abstract
AI-driven code editor extensions such as Visual Studio IntelliCode and Github CoPilot have become extremely popular. These tools recommend inserting chunks of code, with the lines to be inserted presented inline at the current cursor location as gray text. In contrast to their popularity, other AI-driven code recommendation tools that suggest code changes (as opposed to code completions) have remained woefully underused. We conducted lab studies at Microsoft to understand this disparity and found one major cause: discoverability. Code change suggestions are hard to surface through bold, inline interfaces and hence, developers often do not even notice them.Towards a systematic understanding of code change interfaces, we performed a thorough design exploration for various categories of code changes: additive single-line changes, single-line changes, and multi-line changes. Overall, we explored 19 designs through a series of 7 laboratory studies involving 61 programmers and distilled our findings into a set of 5 design principles. To validate our results, we built and deployed a new version of IntelliCode with two of our new inline interfaces in Microsoft Visual Studio 2022 and found that they lead to a significant increase in usage of the corresponding tools.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“Vaithilingam et al. (2023) suggested that automatic inline gray-text suggestions, as opposed to traditional lightbulb interfaces, significantly improve discoverability and usability of CCTs.”
From Understanding user mental models in AI-driven code completion tools: Insights from an elicitation study (2025) · cites this paper as Vaithilingam et al., 2023
In the citing paper
“Other evidence about the misalignment between developers' mental models and CCTs regards the developers' need for finer-grained suggestions and trustworthy explanations (Sergeyuk et al., 2025; Wang et al., 2023), typically not provided in CCTs, as well as the different preferences about inline and sidebar layouts (Vaithilingam et al., 2023; M˘ ar˘ as , oiu et al., 2015).”
From Understanding user mental models in AI-driven code completion tools: Insights from an elicitation study (2025) · cites this paper as Vaithilingam et al., 2023
Citations
Cites
Vaithilingam, P., Zhang, T., & Glassman, E. L. (2022) · CHI Conference on Human Factors in Computing Systems Extended Abstracts · doi:10.1145/3491101.3519665 · Cited by 660
Self-citationHow We Refactor, and How We Know It
Murphy-Hill, E., Parnin, C., & Black, A. P. (2012) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2011.41 · Cited by 547
Grounded Copilot: How Programmers Interact with Code-Generating Models
Barke, S., James, M. B., & Polikarpova, N. (2023) · Proceedings of the ACM on Programming Languages · doi:10.1145/3586030 · Cited by 436
Use, disuse, and misuse of automated refactorings
Vakilian, M., Chen, N., Negara, S., Rajkumar, B. A., Bailey, B. P., & Johnson, R. E. (2012) · 2012 34th International Conference on Software Engineering (ICSE) · doi:10.1109/icse.2012.6227190 · Cited by 106 · cited 2×
“Discoverability: Currently these code suggestions shown via menus like the lightbulb icon (Figure 2) in Visual studio, analogous to Quick Assist in Eclipse, are not discoverable [25].”
BackgroundGrounded Copilot: How Programmers Interact with Code-Generating Models
Barke, S., James, M. B., & Polikarpova, N. (2022) · arXiv · doi:10.48550/arxiv.2206.15000 · Cited by 23
Research works printed but not linked: 23
- nielsen, 2011, Parallel & iterative design + competitive testing = high usability
- 10.1109/ICSE.2012.6227191 · DOI
- groenewegen, 0, Discover quick actions for common tasks as you type with intellicode
- 10.1145/1028014.1028086 · doi:10.1145/1028014.1028086
- murphy-hill, 2008, Making refactoring tools part of the programming workflow
- 2022, Visual studio intellicode Visual studio
- 2022, SSDT for Visual Studio 2022
- 2022, Under the hood of the grammarly editor part two How suggestions work
- 10.1145/3563302 · DOI
- 10.1006/jvlc.1996.0009 · DOI · Paper page
- 10.1109/ASE.2015.39 · DOI
- black, 2008, Better refactoring tools for a better refactoring strategy, IEEE Software
- fowler, 2018, Refactoring Improving the Design of Existing Code
- 10.1145/1240624.1240865 · DOI · Paper page
- 10.1145/1806799.1806866 · DOI · Paper page
- 10.1109/MS.2008.123 · DOI
- 10.1145/3025453.3025645 · DOI
- 10.1109/TSE.2020.3020502 · DOI
- 10.1145/3360569 · DOI · Paper page
- pearce, 2021, Can openai codex and other large language models help us fix security bugs?
- 10.1145/3428287 · DOI
- 2022, Top 10 features of visual studio 2022
- 2021, Github copilot· your ai pair programmer
Cited by
Lau, S., & Guo, P. (2023) · Proceedings of the 2023 ACM Conference on International Computing Education Research V.1 · doi:10.1145/3568813.3600138 · Cited by 241
“prototyped 19 user interface ideas for augmenting IDEs with AI assistance [105].”
MethodA Large-Scale Survey on the Usability of AI Programming Assistants: Successes and Challenges
Liang, J. T., Yang, C., & Myers, B. A. (2023) · arXiv · doi:10.48550/arxiv.2303.17125 · Cited by 206
A Large-Scale Survey on the Usability of AI Programming Assistants: Successes and Challenges
Liang, J. T., Yang, C., & Myers, B. A. (2024) · Proceedings of the IEEE/ACM 46th International Conference on Software Engineering · doi:10.1145/3597503.3608128 · Cited by 203
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
Building Your Own Product Copilot: Challenges, Opportunities, and Needs
Parnin, C., Soares, G., Pandita, R., Gulwani, S., Rich, J., & Henley, A. Z. (2023) · arXiv · doi:10.48550/arxiv.2312.14231 · Cited by 13
Self-citation
Metadata
- Authors
- Vaithilingam, P., Glassman, E. L., Groenwegen, P., Gulwani, S., Henley, A. Z., Malpani, R., Pugh, D., Radhakrishna, A., Soares, G., Wang, J., & Yim, A.
- Affiliations
- Harvard University
- Microsoft
- Venue
- 2023 IEEE/ACM 45th International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP)
- Publisher
- IEEE
- Published
- 2023-05
- Pages
- 185-195
- Cited by
- 24
- References
- 5
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 More Effective AI-Assisted Programming: A Systematic Design Exploration to Improve Visual Studio IntelliCode’s User Experience. https://app.cochat.ai/papers/10.1109/icse-seip58684.2023.00022
- The paper
- Vaithilingam, P., Glassman, E. L., Groenwegen, P., Gulwani, S., Henley, A. Z., Malpani, R., Pugh, D., Radhakrishna, A., Soares, G., Wang, J., & Yim, A. (2023). Towards More Effective AI-Assisted Programming: A Systematic Design Exploration to Improve Visual Studio IntelliCode’s User Experience. 2023 IEEE/ACM 45th International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP). https://doi.org/10.1109/icse-seip58684.2023.00022
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.