Ambar Murillo
Ambar Murillo has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Sarah D'ANgelo
Google, Seattle, USA
5 shared publications - Adam Brown
Google, New York, NY, USA
3 shared publications - Alberto Elizondo
Google, Munich, Germany
3 shared publications - Collin Green
Engineering Productivity Research team, Google, Mountain View, CA, USA
2 shared publications Andrew Macvean
Google, Seattle, WA, USA
1 shared publication- Andrew Macvean
Google, Kirkland, WA, USA
1 shared publication
Latest Publications
- 21 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Software
- Vol. 42 (6) , 17-22
Improving Trust in AI Through Providing Choice
In past installments of our column, we’ve covered ideas about what developers want from AI and how our colleagues have sought to understand and design AI-powered developer tools that humans will trust, adopt, and use to become more productive. We invited some of those same colleagues to contribute their work again in this issue because we’re excited about how AI model quality, tool design, and human behavior come together in this work. Much current research focuses on quantifying the productivity impacts of AI for developers, but this article presents a comprehensive and practical example of the challenge inherent in designing and deploying AI in this manner. We hope that the combination of our prior articles and this one will help others to effectively guide human-centered, AI-driven developer productivity improvements. —Ciera Jaspan and Collin Green
- 21 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Software
- Vol. 42 (6) , 17-22
Improving Trust in AI Through Providing Choice
In past installments of our column, we’ve covered ideas about what developers want from AI and how our colleagues have sought to understand and design AI-powered developer tools that humans will trust, adopt, and use to become more productive. We invited some of those same colleagues to contribute their work again in this issue because we’re excited about how AI model quality, tool design, and human behavior come together in this work. Much current research focuses on quantifying the productivity impacts of AI for developers, but this article presents a comprehensive and practical example of the challenge inherent in designing and deploying AI in this manner. We hope that the combination of our prior articles and this one will help others to effectively guide human-centered, AI-driven developer productivity improvements. —Ciera Jaspan and Collin Green
- Open Access
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-14
Creating benchmarkable components to measure the quality of AI-enhanced developer tools
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-14
Open AccessCreating benchmarkable components to measure the quality of AI-enhanced developer tools
- 29 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Software
- Vol. 42 (3) , 59-66
Seamful AI for Creative Software Engineering: Use in Software Development Workflows
Creativity in software development is frequently overlooked, specifically in the design of developer tools which often focus on productivity. This is likely because creativity is not always seen as a goal in software engineering; in part, this can be explained by the unique way in which software engineers relate to creativity as centered around reusability rather than novelty. However, creativity is a critical aspect of software engineering, and importantly, there is a clear possibility for AI to impact creativity in both positive or negative ways. In this article, we explore the differences in goals for designing AI tools for productivity compared to creativity and propose strategies to elevate creativity in the software engineering workflow. Specifically, we apply seamful design to AI powered software development to consider the role of seamfulness in software development workflows as a way to support creativity.
- 29 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Software
- Vol. 42 (3) , 59-66
Seamful AI for Creative Software Engineering: Use in Software Development Workflows
Creativity in software development is frequently overlooked, specifically in the design of developer tools which often focus on productivity. This is likely because creativity is not always seen as a goal in software engineering; in part, this can be explained by the unique way in which software engineers relate to creativity as centered around reusability rather than novelty. However, creativity is a critical aspect of software engineering, and importantly, there is a clear possibility for AI to impact creativity in both positive or negative ways. In this article, we explore the differences in goals for designing AI tools for productivity compared to creativity and propose strategies to elevate creativity in the software engineering workflow. Specifically, we apply seamful design to AI powered software development to consider the role of seamfulness in software development workflows as a way to support creativity.
- 4 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Software
- Vol. 41 (6) , 23-28
Understanding and Designing for Trust in AI-Powered Developer Tooling
Trust is central to how developers engage with AI. In this article, we discuss what we learned from developers about their level of trust in AI powered developer tooling, and how we translated those findings into product design recommendations to support customization, and the challenges we encountered along the way.
- 4 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Software
- Vol. 41 (6) , 23-28
Understanding and Designing for Trust in AI-Powered Developer Tooling
Trust is central to how developers engage with AI. In this article, we discuss what we learned from developers about their level of trust in AI powered developer tooling, and how we translated those findings into product design recommendations to support customization, and the challenges we encountered along the way.
- Open Access
- 10 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Identifying the Factors That Influence Trust in AI Code Completion
AI-powered software development tooling is changing the way that developers interact with tools and write code. However, the ability for AI to truly transform software development may depend on developers' levels of trust in these tools, which has consequences for tool adoption and repeated usage. In this work, we take a mixed-methods approach to measure the factors that influence developers' trust in AI-powered code completion. We found that characteristics about the AI suggestion itself (e.g., the quality of the suggestion), the developer interacting with the suggestion (e.g., their expertise in a language), and the context of the development work (e.g., was the suggestion in a test file) all influenced acceptance rates of AI-powered code suggestions. Based on these findings we propose a number of recommendations for the design of AI-powered development tools to improve trust.
- 10 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Open AccessIdentifying the Factors That Influence Trust in AI Code Completion
AI-powered software development tooling is changing the way that developers interact with tools and write code. However, the ability for AI to truly transform software development may depend on developers' levels of trust in these tools, which has consequences for tool adoption and repeated usage. In this work, we take a mixed-methods approach to measure the factors that influence developers' trust in AI-powered code completion. We found that characteristics about the AI suggestion itself (e.g., the quality of the suggestion), the developer interacting with the suggestion (e.g., their expertise in a language), and the context of the development work (e.g., was the suggestion in a test file) all influenced acceptance rates of AI-powered code suggestions. Based on these findings we propose a number of recommendations for the design of AI-powered development tools to improve trust.
- Open Access
- 12 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-12
GenderMag Improves Discoverability in the Field, Especially for Women
Prior research shows that the GenderMag method can help identify and address usability barriers that are more likely to affect women software users than men. However, the evidence for the effectiveness of GenderMag is limited to small lab studies. In this case study, by combining self-reported gender data from tens of thousands of users of an internal code review tool with software logs data gathered over a five-year period, we quantitatively show that GenderMag helped a team at Google (a) correctly identify discoverability as a usability barrier more likely to affect women than men, and (b) increase discoverability by 2.4x while also achieving gender parity. That is, compared to men using the original code review tool, women and men using the system redesigned with GenderMag were both 2.4x more likely to discover the "Suggest Edit" feature at any given time. Thus, this paper contributes the first large-scale evidence of the effectiveness of GenderMag in the field.
- 12 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Open AccessGenderMag Improves Discoverability in the Field, Especially for Women
Prior research shows that the GenderMag method can help identify and address usability barriers that are more likely to affect women software users than men. However, the evidence for the effectiveness of GenderMag is limited to small lab studies. In this case study, by combining self-reported gender data from tens of thousands of users of an internal code review tool with software logs data gathered over a five-year period, we quantitatively show that GenderMag helped a team at Google (a) correctly identify discoverability as a usability barrier more likely to affect women than men, and (b) increase discoverability by 2.4x while also achieving gender parity. That is, compared to men using the original code review tool, women and men using the system redesigned with GenderMag were both 2.4x more likely to discover the "Suggest Edit" feature at any given time. Thus, this paper contributes the first large-scale evidence of the effectiveness of GenderMag in the field.