Loop Engineering: Building Blocks, Adoption, and Impact (Supplementary Material)

Over the past months, the way developers guide agentic AI coding tools has moved up several levels of abstraction, from phrasing prompts to engineering context to configuring the harness around the underlying model. In June 2026, practitioners began to describe a new level called loop engineering: Instead of prompting an agent interactively, developers design systems that prompt agents for them. The term spread rapidly, accompanied by bold claims and vocal skepticism, but its adoption in software projects has not yet been measured. We present (1) an exploratory review of the emerging gray literature on loop engineering, (2) an exploratory mining study of 36,710 software repositories, with an analysis of which aspects of loop engineering are traceable from repository data, and (3) a research agenda derived from that review to empirically study loop engineering in open-source projects. The reviewed sources largely agree on what a well-engineered loop contains: agent runs started on a schedule or by repository events and bounded by machine-checkable stop conditions, persistent state files, verifier subagents, token budgets, and defined points of escalation to humans. We confirmed autonomous agent loops in 217 of the 256 repositories that our heuristics and behavioral signals matched. Nearly all of these repositories committed the configuration that starts their loops, but almost none of them committed the state files that the gray literature recommends. We conclude by outlining a controlled study of agent autonomy levels and their effect on task success, cost, and developer effort.