SWE-chat: Coding Agent Interactions From Real Users in the Wild

TL;DR

SWE-chat is a large-scale, real-world dataset of coding agent interactions revealing usage patterns, failure modes, and user behaviors in natural developer workflows.

Contribution

It introduces SWE-chat, the first extensive dataset of real open-source developer-agent sessions, enabling empirical analysis of practical AI coding agent use.

Findings

41% of sessions involve agents authoring almost all code

Only 44% of agent-generated code is committed by users

Agent-written code has more security vulnerabilities than human code

Abstract

AI coding agents are being adopted at scale, yet we lack empirical evidence on how people actually use them and how much of their output is useful in practice. We present SWE-chat, the first large-scale dataset of real coding agent sessions collected from open-source developers in the wild. The dataset currently contains 6,000 sessions, comprising more than 63,000 user prompts and 355,000 agent tool calls. SWE-chat is a living dataset; our collection pipeline automatically and continually discovers and processes sessions from public repositories. Leveraging SWE-chat, we provide an initial empirical characterization of real-world coding agent usage and failure modes. We find that coding patterns are bimodal: in 41% of sessions, agents author virtually all committed code ("vibe coding"), while in 23%, humans write all code themselves. Despite rapidly improving capabilities, coding agents remain inefficient in natural settings. Just 44% of all agent-produced code survives into user commits, and agent-written code introduces more security vulnerabilities than code authored by humans. Furthermore, users push back against agent outputs -- through corrections, failure reports, and interruptions -- in 44% of all turns. By capturing complete interaction traces with human vs. agent code authorship attribution, SWE-chat provides an empirical foundation for moving beyond curated benchmarks towards an evidence-based understanding of how AI agents perform in real developer workflows.