Codeon is the intelligent assistant for software developers

Researchers, including Profs. Walter S. Lasecki and Steve Oney, CS undergraduate student Yiwei Yang, and CSE graduate students Yan Chen, Yin Xie, and Sang Won Lee have created Codeon, a system that enables more effective task hand-off between end-user developers and remote helpers by allowing asynchronous responses to on-demand requests. With Codeon, developers can request help by speaking their requests aloud within the context of their Integrated Development Environment (IDE).

Codeon automatically captures the relevant code context and allows remote helpers to respond with high-level descriptions, code annotations, code snippets, and natural language explanations. Developers can then immediately view and integrate these responses into their code. It makes it easy for developers to make sufficiently detailed requests and send to other developers, making the process quick and effective. Codeon’s asynchronous model also scalable more effectively for multiple helpers than synchronous support tools because it allows multiple helpers to work in parallel with the developer.

The researchers found that developers using Codeon completed nearly twice as many tasks as those who used state-of-the-art synchronous video and code sharing tools, thanks to the reduction in coordination costs of seeking assistance from other developers.