Envisioning the Next-Generation AI Coding Assistants: Insights & Proposals
This work addresses the design and implementation challenges of AI coding assistants for software developers, but it is incremental as it builds on existing practices without introducing new methods or data.
The authors analyzed their experience developing AI coding assistants to identify key design principles, such as setting clear expectations and integrating with IDE capabilities, and proposed open challenges for future research and industry development.
As a research-product hybrid group in AI for Software Engineering (AI4SE), we present four key takeaways from our experience developing in-IDE AI coding assistants. AI coding assistants should set clear expectations for usage, integrate with advanced IDE capabilities and existing extensions, use extendable backend designs, and collect app data responsibly for downstream analyses. We propose open questions and challenges that academia and industry should address to realize the vision of next-generation AI coding assistants.