arXiv subjects

Andrew Macvean

Publications and source records attributed to Andrew Macvean.

8 recordsLinked to original sources

arXiv2026

The Perfection Paradox: From Architect to Curator in AI-Assisted API Design

Enterprise API design is often bottlenecked by the tension between rapid feature delivery and the rigorous maintenance of usability standards. We present an industrial case study evaluating an AI-assisted design workflow trained on API Improvement Proposals (AIPs). Through a controlled study with 16 industry experts, we compared AI-generated API specifications against human-authored ones. While quantitative results indicated AI superiority in 10 of 11 usability dimensions and an 87% reduction in authoring time, qualitative analysis revealed a paradox: experts frequently misidentified AI work as human (19% accuracy) yet described the designs as unsettlingly "perfect." We characterize this as a "Perfection Paradox" -- where hyper-consistency signals a lack of pragmatic human judgment. We discuss the implications of this perfection paradox, proposing a shift in the human designer's role from the "drafter" of specifications to the "curator" of AI-generated patterns.

cs.SE↗

arXiv2025

From Correctness to Collaboration: Toward a Human-Centered Framework for Evaluating AI Agent Behavior in Software Engineering

As Large Language Models (LLMs) evolve from code generators into collaborative partners for software engineers, our methods for evaluation are lagging. Current benchmarks, focused on code correctness, fail to capture the nuanced, interactive behaviors essential for successful human-AI partnership. To bridge this evaluation gap, this paper makes two core contributions. First, we present a foundational taxonomy of desirable agent behaviors for enterprise software engineering, derived from an analysis of 91 sets of user-defined agent rules. This taxonomy defines four key expectations of agent behavior: Adhere to Standards and Processes, Ensure Code Quality and Reliability, Solving Problems Effectively, and Collaborating with the User. Second, recognizing that these expectations are not static, we introduce the Context-Adaptive Behavior (CAB) Framework. This emerging framework reveals how behavioral expectations shift along two empirically-derived axes: the Time Horizon (from immediate needs to future ideals), established through interviews with 15 expert engineers, and the Type of Work (from enterprise production to rapid prototyping, for example), identified through a prompt analysis of a prototyping agent. Together, these contributions offer a human-centered foundation for designing and evaluating the next generation of AI agents, moving the field's focus from the correctness of generated code toward the dynamics of true collaborative intelligence.

cs.SE↗

arXiv2025

What do professional software developers need to know to succeed in an age of Artificial Intelligence?

Generative AI is showing early evidence of productivity gains for software developers, but concerns persist regarding workforce disruption and deskilling. We describe our research with 21 developers at the cutting edge of using AI, summarizing 12 of their work goals we uncovered, together with 75 associated tasks and the skills & knowledge for each, illustrating how developers use AI at work. From all of these, we distilled our findings in the form of 5 insights. We found that the skills & knowledge to be a successful AI-enhanced developer are organized into four domains (using Generative AI effectively, core software engineering, adjacent engineering, and adjacent non-engineering) deployed at critical junctures throughout a 6-step task workflow. In order to "future proof" developers for this age of AI, on-the-job learning initiatives and computer science degree programs will need to target both "soft" skills and the technical skills & knowledge in all four domains to reskill, upskill and safeguard against deskilling.

cs.AI↗

arXiv2025

Creating benchmarkable components to measure the quality ofAI-enhanced developer tools

In the AI community, benchmarks to evaluate model quality are well established, but an equivalent approach to benchmarking products built upon generative AI models is still missing. This has had two consequences. First, it has made teams focus on model quality over the developer experience, while successful products combine both. Second, product team have struggled to answer questions about their products in relation to their competitors. In this case study, we share: (1) our process to create robust, enterprise-grade and modular components to support the benchmarking of the developer experience (DX) dimensions of our team's AI for code offerings, and (2) the components we have created to do so, including demographics and attitudes towards AI surveys, a benchmarkable task, and task and feature surveys. By doing so, we hope to lower the barrier to the DX benchmarking of genAI-enhanced code products.

cs.SE↗

arXiv2024

How much does AI impact development speed? An enterprise-based randomized controlled trial

How much does AI assistance impact developer productivity? To date, the software engineering literature has provided a range of answers, targeting a diversity of outcomes: from perceived productivity to speed on task and developer throughput. Our randomized controlled trial with 96 full-time Google software engineers contributes to this literature by sharing an estimate of the impact of three AI features on the time developers spent on a complex, enterprise-grade task. We found that AI significantly shortened the time developers spent on task. Our best estimate of the size of this effect, controlling for factors known to influence developer time on task, stands at about 21\%, although our confidence interval is large. We also found an interesting effect whereby developers who spend more hours on code-related activities per day were faster with AI. Product and future research considerations are discussed. In particular, we invite further research that explores the impact of AI at the ecosystem level and across multiple suites of AI-enhanced tools, since we cannot assume that the effect size obtained in our lab study will necessarily apply more broadly, or that the effect of AI found using internal Google tooling in the summer of 2024 will translate across tools and over time.

cs.SE↗

arXiv2023

Understanding Documentation Use Through Log Analysis: An Exploratory Case Study of Four Cloud Services

Almost no modern software system is written from scratch, and developers are required to effectively learn to use third-party libraries or software services. Thus, many practitioners and researchers have looked for ways to create effective documentation that supports developers' learning. However, few efforts have focused on how people actually use the documentation. In this paper, we report on an exploratory, multi-phase, mixed methods empirical study of documentation page-view logs from four cloud-based industrial services. By analyzing page-view logs for over 100,000 users, we find diverse patterns of documentation page visits. Moreover, we show statistically that which documentation pages people visit often correlates with user characteristics such as past experience with the specific product, on the one hand, and with future adoption of the API on the other hand. We discuss the implications of these results on documentation design and propose documentation page-view log analysis as a feasible technique for design audits of documentation, from ones written for software developers to ones designed to support end users (e.g., Adobe Photoshop).

cs.SE↗

arXiv2023

Using an LLM to Help With Code Understanding

Understanding code is challenging, especially when working in new and complex development environments. Code comments and documentation can help, but are typically scarce or hard to navigate. Large language models (LLMs) are revolutionizing the process of writing code. Can they do the same for helping understand it? In this study, we provide a first investigation of an LLM-based conversational UI built directly in the IDE that is geared towards code understanding. Our IDE plugin queries OpenAI's GPT-3.5-turbo model with four high-level requests without the user having to write explicit prompts: to explain a highlighted section of code, provide details of API calls used in the code, explain key domain-specific terms, and provide usage examples for an API. The plugin also allows for open-ended prompts, which are automatically contextualized to the LLM with the program being edited. We evaluate this system in a user study with 32 participants, which confirms that using our plugin can aid task completion more than web search. We additionally provide a thorough analysis of the ways developers use, and perceive the usefulness of, our system, among others finding that the usage and benefits differ between students and professionals. We conclude that in-IDE prompt-less interaction with LLMs is a promising future direction for tool builders.

cs.SE↗

arXiv2022

Understanding How Programmers Can Use Annotations on Documentation

Modern software development requires developers to find and effectively utilize new APIs and their documentation, but documentation has many well-known issues. Despite this, developers eventually overcome these issues but have no way of sharing what they learned. We investigate sharing this documentation-specific information through \textit{annotations}, which have advantages over developer forums as the information is contextualized, not disruptive, and is short, thus easy to author. Developers can also author annotations to support their own comprehension. In order to support the documentation usage behaviors we found, we built the Adamite annotation tool, which supports features such as multi-anchoring, annotation types, and pinning. In our user study, we found that developers are able to create annotations that are useful to themselves and are able to utilize annotations created by other developers when learning a new API, with readers of the annotations completing 67% more of the task, on average, than the baseline.

cs.HC↗