Harini Sampath

Harini has been at Google since March 2016, conducting research into developer experience. Her areas of interest are command line interfaces, APIs, documentation and accessibility of developer tools.
Authored Publications
Sort By
  • Title
  • Title, descending
  • Year
  • Year, descending
    From Correctness to Collaboration: A Human-Centered Taxonomy of AI Agent Behavior in Software Engineering
    Sherry Y. Shi
    Extended Abstracts of the 2026 CHI Conference on Human Factors in Computing Systems (CHI EA ’26), ACM, New York, NY, USA (2026)
    Preview abstract The ongoing transition of Large Language Models in software engineering from code generators into autonomous agents requires a shift in how we define and measure success. While models are becoming more capable, the industry lacks a clear understanding of the behavioral norms that make an agent effective in collaborative software development in the enterprise. This work addresses this gap by presenting a taxonomy of desirable agent behaviors, synthesized from 91 sets of user-defined rules for coding agents. We identify four core expectations: Adhere to Standards and Processes, Ensure Code Quality and Reliability, Solve Problems Effectively, and Collaborate with the User. These findings offer a concrete vocabulary for agent behavior, enabling researchers to move beyond correctness-only benchmarks and design evaluations that reflect the realities of professional software development in large enterprises. View details
    Accessibility of Command Line Interfaces
    Alice Merrick
    CHI Conference on Human Factors in Computing Systems (2021)
    Preview abstract Command line interfaces (CLIs) remain a popular tool among developers and system administrators. Since CLIs are text based interfaces, they are sometimes considered accessible alternatives to predominantly visual developer tools like IDEs. However, there is no systematic evaluation of accessibility of CLIs in the literature. In this paper, we describe two studies with 12 developers on their experience of using CLIs with screen readers. Our findings show that CLIs have their own set of accessibility issues - the most important being CLIs are unstructured text interfaces. Based on our findings, we provide a set of recommendations for improving accessibility of command line interfaces. View details
    Preview abstract Many efforts to increase accessibility in coding for developers with visual impairments (DWVI) have focused on supporting interactions with interactive development environments and source code. However, in order to understand how to appropriately modify and write source code, developers must seek and synthesize information from a variety of disparate and highly technical sources. DWVI might benefit from technological support in this process. But, it is unclear what accessibility issues arise in technical information sources, whether accessibility impacts strategies for seeking technical information, or how best to support DWVI in this process. We conducted observations and interviews with twelve DWVI, about their information seeking behaviors. We found that, DWVI seek information in many of the same sources as their sighted peers, and the accessibility issues identified in technical information sources were similar to those in nontechnical sources. Yet, despite these similarities, accessibility considerations impacted information seeking in highly nuanced ways. View details
    ×