Problem
Research questions and friction points this paper is trying to address.
AI systems
developer workflow
bounded delegation
AI-assisted development
task automation
To Copilot and Beyond: 22 AI Systems Developers Want Built
🤖 AI Summary
This study addresses the disproportionate focus of current AI development tools on code generation—a task constituting only about 10% of developers’ work—while neglecting support needs and intervention boundaries in the remaining 90%. Through qualitative interviews with 860 Microsoft developers, combined with human-AI collaboration and a multi-model committee-based thematic analysis, the research identifies 22 high-priority AI system concepts across five task categories. It proposes a “bounded delegation” paradigm, wherein developers prefer AI to assist with peripheral assembly tasks rather than core programming. Effective delegation requires mechanisms such as quality signals, scoped permissions, provenance tracing, and uncertainty indicators. These findings offer concrete design directions and constraint frameworks for next-generation AI-powered development tools.
📝 Abstract
Developers spend roughly one-tenth of their workday writing code, yet most AI tooling targets that fraction. This paper asks what should be built for the rest. We surveyed 860 Microsoft developers to understand where they want AI support, and where they want it to stay out. Using a human-in-the-loop, multi-model council-based thematic analysis, we identify 22 AI systems that developers want built across five task categories. For each, we describe the problem it solves, what makes it hard to build, and the constraints developers place on its behavior. Our findings point to a growing right-shift burden in AI-assisted development: developers wanted systems that embed quality signals earlier in their workflow to keep pace with accelerating code generation, while enforcing explicit authority scoping, provenance, uncertainty signaling, and least-privilege access throughout. This tension reveals a pattern we call "bounded delegation": developers wanted AI to absorb the assembly work surrounding their craft, never the craft itself. That boundary tracks where they locate professional identity, suggesting that the value of AI tooling may lie as much in where and how precisely it stops as in what it does.
Innovation
Methods, ideas, or system contributions that make the work stand out.
bounded delegation
human-in-the-loop
thematic analysis
AI-assisted development
developer workflow
🔎 Similar Papers
No similar papers found.
