To Copilot and Beyond: 22 AI Systems Developers Want Built

TL;DR

This study surveys Microsoft developers to identify 22 desired AI tools for supporting various coding tasks, emphasizing quality, authority, and provenance constraints to align AI assistance with professional identity.

Contribution

It introduces a thematic analysis revealing developers' priorities and constraints for AI tools, highlighting the concept of 'bounded delegation' in AI-assisted development.

Findings

Developers want AI to embed quality signals early in workflows.

Constraints include authority scoping, provenance, and uncertainty signaling.

AI should support assembly work without replacing core craft skills.

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.