# Do AI Coding Agents Write Infrastructure as Code Like Humans? An Empirical Study of GitHub Pull Requests

DevFeed: [Do AI Coding Agents Write Infrastructure as Code Like Humans? An Empirical Study of GitHub Pull Requests](<https://devfeed.tech/articles/do-ai-coding-agents-write-infrastructure-as-code-like-humans-an-empirical-study-of-github-pull-requests-101780.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.34613>)

Author: Amine Barrak, Emna Ksontini, Charles Wehbe

Published: 2026-10-27T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Terraform](<https://devfeed.tech/topics/terraform.md>), [GitHub](<https://devfeed.tech/topics/github.md>), [coding assistant](<https://devfeed.tech/topics/coding-assistant.md>)

Tags: [ai-coding-agents](<https://devfeed.tech/tags/ai-coding-agents.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [github](<https://devfeed.tech/tags/github.md>), [infrastructure-as-code](<https://devfeed.tech/tags/infrastructure-as-code.md>), [pull-requests](<https://devfeed.tech/tags/pull-requests.md>), [study](<https://devfeed.tech/tags/study.md>), [sustainability](<https://devfeed.tech/tags/sustainability.md>), [terraform](<https://devfeed.tech/tags/terraform.md>)

## AI overview

Across 349,156 IaC pull requests from 49,241 GitHub repositories, agent contributions were about four times larger than human PRs and more often changed core infrastructure; automation bots mainly maintained dependencies. Silent-agent PRs had a higher overall merge rate than human PRs (87.4% vs. 78.9%), but a 4.0-point lower rate within the same repositories. Disclosed agents created new infrastructure more often (34.0% vs. 21.4%) and were 8.4 points less likely to have PRs merged for the same change type within a repository; silent agents had comparable acceptance for most change types. In 2,645 matched Terraform PR pairs, agent and human PRs showed similar rates of sustainability smells (10.4% vs. 10.3%; paired odds ratio 1.02, 95% CI 0.83-1.25), commonly missing remote state and monolithic configurations. The study also found agent traces in 12.3% of PRs remaining after bot identification, with that share increasing over time.

## Source excerpt

arXiv:2610.34613v1 Announce Type: new Abstract: Infrastructure-as-Code (IaC) configurations define cloud resources, networking, and access control, and AI coding agents increasingly write them. Little is known about how agent contributions differ from those of humans and automation bots, how maintainers evaluate them, and whether they introduce different sustainability concerns. We study 349,156 IaC pull requests (PRs) from 49,241 GitHub repositories, distinguishing humans, automation bots, silent agents, and disclosed agents. Bots account for 32.9% of ostensibly human PRs, and 12.3% of the remaining PRs contain agent traces, a share that grows over the study period. Agent PRs are about four times larger than human PRs and more often modify core infrastructure modules, whereas bots mainly maintain dependencies. Silent-agent PRs have higher overall merge rates than human PRs (87.4% vs. 78.9%) but are merged 4.0 percentage points less often within the same repositories. Disclosed agents create new infrastructure more often than humans (34.0% vs. 21.4%), and even for the same change type within the same repository, their PRs are 8.4 points less likely to be merged; silent-agent PRs show comparable acceptance for most change types. Finally, in 2,645 matched agent-human Terraform PR pairs, agent and human PRs introduce sustainability smells at similar rates (10.4% vs. 10.3%; paired odds ratio 1.02, 95% CI 0.83-1.25), most commonly missing remote state and monolithic configurations.