To Copilot and Beyond: 22 AI Systems Developers Want Built

• URL: http://arxiv.org/abs/2604.07830v1
• Date: Thu, 09 Apr 2026 05:31:34 GMT
• Title: To Copilot and Beyond: 22 AI Systems Developers Want Built
• Abstract summary: We surveyed 860 Microsoft developers to understand where they want AI support, and where they want it to stay out.<n>We identify 22 AI systems that developers want built across five task categories.<n>For each, we describe the problem it solves, what makes it hard to build, and the constraints developers place on its behavior.
• Score: 8.021702941771972
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• How Do Developers Interact with AI? An Exploratory Study on Modeling Developer Programming Behavior [8.956327421839205]
  We show how hidden intentions and emotional dimensions intertwine with concrete actions during AI-assisted programming.<n>Using AI assistants often makes developers more focused on actively creating code, evaluating, and verifying generated results.<n>Some developers reported impostor-like feelings, expressing guilt or self-doubt about relying on AI.
  arXiv  Detail & Related papers  (2026-03-28T14:37:19Z)
• AI Where It Matters: Where, Why, and How Developers Want AI Support in Daily Work [3.1984206905916]
  Generative AI is reshaping software work, yet we lack clear guidance on where developers most need and want support.<n>We report a large-scale, mixed-methods study of N=860 developers that examines where, why, and how they seek or limit AI help.<n>Our results offer concrete, contextual guidance for delivering AI where it matters to developers and their work.
  arXiv  Detail & Related papers  (2025-10-01T10:51:03Z)
• The Rise of AI Teammates in Software Engineering (SE) 3.0: How Autonomous Coding Agents Are Reshaping Software Engineering [10.252332355171237]
  This paper introduces AIDev, the first largescale dataset capturing how such agents operate in the wild.<n>Spanning over 456,000 pull requests by five leading agents, AIDev provides an unprecedented empirical foundation for studying autonomous teammates in software development.<n>The dataset includes rich on PRs, authorship, review timelines, code changes, and integration outcomes.
  arXiv  Detail & Related papers  (2025-07-20T15:15:58Z)
• Code with Me or for Me? How Increasing AI Automation Transforms Developer Workflows [60.04362496037186]
  We present the first controlled study of developer interactions with coding agents.<n>We evaluate two leading copilot and agentic coding assistants.<n>Our results show agents can assist developers in ways that surpass copilots.
  arXiv  Detail & Related papers  (2025-07-10T20:12:54Z)
• SciMaster: Towards General-Purpose Scientific AI Agents, Part I. X-Master as Foundation: Can We Lead on Humanity's Last Exam? [51.112225746095746]
  We introduce X-Master, a tool-augmented reasoning agent designed to emulate human researchers.<n>X-Masters sets a new state-of-the-art record on Humanity's Last Exam with a score of 32.1%.
  arXiv  Detail & Related papers  (2025-07-07T17:50:52Z)
• What do professional software developers need to know to succeed in an age of Artificial Intelligence? [1.5774644021279332]
  Generative AI is showing early evidence of productivity gains for software developers, but concerns persist regarding workforce disruption and deskilling.<n>We describe our research with 21 developers at the cutting edge of using AI, summarizing 12 of their work goals we uncovered, together with 75 associated tasks and the skills & knowledge for each.<n>We found that the skills & knowledge to be a successful AI-enhanced developer are organized into four domains.
  arXiv  Detail & Related papers  (2025-05-30T20:14:03Z)
• Explainability for Embedding AI: Aspirations and Actuality [1.8130068086063336]
  Explainable AI (XAI) may allow developers to understand better the systems they build.<n>Existing XAI systems still fall short of this aspiration.<n>We see an unmet need to provide developers with adequate support mechanisms to cope with this complexity.
  arXiv  Detail & Related papers  (2025-04-20T14:20:01Z)
• From Teacher to Colleague: How Coding Experience Shapes Developer Perceptions of AI Tools [0.0]
  AI-assisted development tools promise productivity gains and improved code quality, yet their adoption among developers remains inconsistent.<n>We analyze survey data from 3380 developers to examine how coding experience relates to AI awareness, adoption, and the roles developers assign to AI in their workflow.
  arXiv  Detail & Related papers  (2025-04-08T08:58:06Z)
• Challenges and Paths Towards AI for Software Engineering [55.95365538122656]
  We discuss progress in AI for software engineering in threefold manner.<n>First, we provide a structured taxonomy of concrete tasks in AI for software engineering.<n>Second, we outline several key bottlenecks that limit current approaches.
  arXiv  Detail & Related papers  (2025-03-28T17:17:57Z)
• Cybertrust: From Explainable to Actionable and Interpretable AI (AI2) [58.981120701284816]
  Actionable and Interpretable AI (AI2) will incorporate explicit quantifications and visualizations of user confidence in AI recommendations. It will allow examining and testing of AI system predictions to establish a basis for trust in the systems' decision making.
  arXiv  Detail & Related papers  (2022-01-26T18:53:09Z)
• A User-Centred Framework for Explainable Artificial Intelligence in Human-Robot Interaction [70.11080854486953]
  We propose a user-centred framework for XAI that focuses on its social-interactive aspect. The framework aims to provide a structure for interactive XAI solutions thought for non-expert users.
  arXiv  Detail & Related papers  (2021-09-27T09:56:23Z)
• The MineRL BASALT Competition on Learning from Human Feedback [58.17897225617566]
  The MineRL BASALT competition aims to spur forward research on this important class of techniques. We design a suite of four tasks in Minecraft for which we expect it will be hard to write down hardcoded reward functions. We provide a dataset of human demonstrations on each of the four tasks, as well as an imitation learning baseline.
  arXiv  Detail & Related papers  (2021-07-05T12:18:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.