The Future of Development Environments with AI Foundation Models: NII Shonan Meeting 222 Report
Xing Hu, Raula Gaikovina Kula, Christoph Treude
TL;DR
The paper reports on NII Shonan Meeting 222, a cross-disciplinary workshop exploring how AI foundation models will reshape development environments. It frames a spectrum from evolutionary to revolutionary changes, arguing that GenAI will raise abstraction and shift routine coding tasks to automation while preserving human design and governance. It introduces concepts such as prompt-as-documentation, persona-driven adaptive IDEs, and holodeck-like simulators to reason about software, and discusses critical challenges in data management, transparency, privacy, and ethics. The work highlights four breakout perspectives and outlines a research trajectory for aligning GenAI hype with real‑world software engineering practice.
Abstract
Generative Artificial Intelligence (GenAI) models are achieving remarkable performance in various tasks, including code generation, testing, code review, and program repair. The ability to increase the level of abstraction away from writing code has the potential to change the Human-AI interaction within the integrated development environment (IDE). To explore the impact of GenAI on IDEs, 33 experts from the Software Engineering, Artificial Intelligence, and Human-Computer Interaction domains gathered to discuss challenges and opportunities at Shonan Meeting 222. This is the report