Developer Experiences with a Contextualized AI Coding Assistant: Usability, Expectations, and Outcomes
CoRR(2023)
摘要
In the rapidly advancing field of artificial intelligence, software
development has emerged as a key area of innovation. Despite the plethora of
general-purpose AI assistants available, their effectiveness diminishes in
complex, domain-specific scenarios. Noting this limitation, both the academic
community and industry players are relying on contextualized coding AI
assistants. These assistants surpass general-purpose AI tools by integrating
proprietary, domain-specific knowledge, offering precise and relevant
solutions. Our study focuses on the initial experiences of 62 participants who
used a contextualized coding AI assistant -- named StackSpot AI -- in a
controlled setting. According to the participants, the assistants' use resulted
in significant time savings, easier access to documentation, and the generation
of accurate codes for internal APIs. However, challenges associated with the
knowledge sources necessary to make the coding assistant access more contextual
information as well as variable responses and limitations in handling complex
codes were observed. The study's findings, detailing both the benefits and
challenges of contextualized AI assistants, underscore their potential to
revolutionize software development practices, while also highlighting areas for
further refinement.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要