Programming by Chat: A Large-Scale Behavioral Analysis of 11,579 Real-World AI-Assisted IDE Sessions

TL;DR

This large-scale study analyzes real-world AI-assisted IDE sessions, revealing how developers iteratively collaborate with AI, delegate cognitive tasks, and manage AI interactions during programming.

Contribution

First comprehensive empirical analysis of real-world conversational programming in IDEs, highlighting new collaboration patterns and cognitive shifts with AI assistants.

Findings

Programming is iterative, with developers refining outputs over time.

Developers delegate diagnosis, comprehension, and validation to AI.

Collaboration involves externalizing plans and managing AI autonomy.

Abstract

IDE-integrated AI coding assistants, which operate conversationally within developers' working codebases with access to project context and multi-file editing, are rapidly reshaping software development. However, empirical investigation of this shift remains limited: existing studies largely rely on small-scale, controlled settings or analyze general-purpose chatbots rather than codebase-aware IDE workflows. We present, to the best of our knowledge, the first large-scale study of real-world conversational programming in IDE-native settings, analyzing 74,998 developer messages from 11,579 chat sessions across 1,300 repositories and 899 developers using Cursor and GitHub Copilot. These chats were committed to public repositories as part of routine development, capturing in-the-wild behavior. Our findings reveal three shifts in how programming work is organized: conversational programming operates as progressive specification, with developers iteratively refining outputs rather than specifying complete tasks upfront; developers redistribute cognitive work to AI, delegating diagnosis, comprehension, and validation rather than engaging with code and outputs directly; and developers actively manage the collaboration, externalizing plans into persistent artifacts, and negotiating AI autonomy through context injection and behavioral constraints. These results provide foundational empirical insights into AI-assisted development and offer implications for the design of future programming environments.