About the Author

James C. Davis is an assistant professor in the Elmore Family School of Electrical and Computer Engineering at Purdue University, where he leads a research group in software engineering with applications in systems and cybersecurity. His work appears at venues such as ICSE and IEEE S&P and has been recognized with three ACM SIGSOFT distinguished paper awards; he received the NSF CAREER award in 2026. His lab is supported by the NSF, Google, Rolls-Royce, Cisco, Socket, and OpenAI.

He came to the professoriate by way of industry. He spent five years as a software engineer at IBM (2012–2015), where he wrote roughly a hundred thousand lines of Perl and C/C++ test infrastructure, trained engineers at international sites, and — a distinction he offers with a straight face — held his team's one-year record for defects opened: the badge of someone whose job was to find the bugs, not to ship them. He earned his PhD from Virginia Tech in 2020. Counting the five years in industry, five in graduate school, and six on the faculty, the methodology in this book rests on sixteen years of software engineering that straddles the GenAI divide — the pre-GenAI half spent writing that same hundred thousand lines by hand, in C/C++, Perl, and Python, and the recent half spent, as these chapters describe, building a production system almost entirely by directing a fleet of coding agents.

This book is the field report from that build. DocAble, the document-accessibility service it describes, is live at scholaccess.com.