Abstract
A disclosed technology can address challenges in managing new software bugs when engineering capacity is limited, a situation which can be impacted by time-consuming initial investigations. The technology can provide a structured, human-in-the-loop workflow where a bug reporter may use an artificial intelligence (AI) assistant, such as a large language model, to perform a preliminary analysis at the point of bug discovery. This process, which can be guided by structured prompts, may generate an enriched bug report containing analysis from the AI, including, for example, potential root causes, code pointers, and ownership suggestions. By shifting a portion of the initial investigative work from an engineering team to the reporter, this method may reduce the triage and diagnostic burden on engineers, potentially enabling more efficient use of limited resources and helping to accelerate bug resolution.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Leung, Mira, "Human-in-the-Loop Workflow for AI-Assisted Preliminary Bug Investigation", Technical Disclosure Commons, (April 24, 2026)
https://www.tdcommons.org/dpubs_series/9920