When AI Agents Touch CI/CD Configurations: Frequency and Success

TL;DR

This study analyzes how AI agents interact with CI/CD configurations in open-source projects, revealing they rarely modify configurations but do so reliably, especially with GitHub Actions, and highlighting differences among agents like Copilot.

Contribution

It provides the first large-scale analysis of AI agent modifications to CI/CD configs, showing their focus on GitHub Actions and comparable success rates to human changes.

Findings

AI agents modify CI/CD configs in 3.25% of their changes.

Most CI/CD modifications target GitHub Actions.

AI modifications to CI/CD are as successful as human changes.

Abstract

AI agents are increasingly used in software development, yet their interaction with CI/CD configurations is not well studied. We analyze 8,031 agentic pull requests (PRs) from 1,605 GitHub repositories where AI agents touch YAML configurations. CI/CD configuration files account for 3.25% of agent changes, varying by agent (Devin: 4.83%, Codex: 2.01%, p < 0.001). When agents modify CI/CD, 96.77% target GitHub Actions. Agentic PRs with CI/CD changes merge slightly less often than others (67.77% vs. 71.80%), except for Copilot, whose CI/CD changes merge 15.63 percentage points more often. Across 99,930 workflow runs, build success rates are comparable for CI/CD and non-CI/CD changes (75.59% vs. 74.87%), though three agents show significantly higher success when modifying CI/CD. These results show that AI agents rarely modify CI/CD and focus mostly on GitHub Actions, yet their configuration changes are as reliable as regular code. Copilot's strong CI/CD performance despite lower acceptance suggests emerging configuration specialization, with implications for agent training and DevOps automation.