The authors analyze the ability of ChatGPT to generate effective instructions for a consequential task: taking a COVID-19 test. They compare the output from a commercial prompt for generating these instructions to those provided by the test manufacturer. They also analyze the input, the prompt itself, to address prompt-engineering issues. The results show that although the output from ChatGPT exhibits certain conventions for documentation, the human-authored instructions from the manufacturer are superior in most ways. The authors conclude that when it comes to creating high-quality, consequential instructions, ChatGPT might be better seen as a collaborator than a competitor with human technical communicators.

Despite their central importance to a variety of endeavors and despite widespread use in both industry and academia, version control systems (software for tracking versions of files) have not been extensively studied in fields related to technical communication, rhetoric, and communication design. Git, by far the most dominant version control system today, is largely absent. This study theorizes Git as boundary infrastructure---infrastructure used to facilitate collaboration across disciplines and domains. The unique characteristics of boundary infrastructure explain how something as prominent as Git can be so invisible and help identify dangers posed by boundary infrastructure. Drawing on modes of resistance developed in feminist rhetorics, this article concludes with suggestions to ameliorate the negatives effects such infrastructure might have on collaborative knowledge work.