Autonomy Is a Property of the Operation: A Framework for Deciding What DevOps Agents May Do Unattended
- 1Beamreach Intelligence LDA
Abstract
Automation moved the execution of operational work off engineers but not their attention: someone still has to look, judge and approve, and that person has become the bottleneck. As agents built on large language models widen what a DevOps system can do, deciding what an agent may do without a human looking is now a practical configuration question. We argue that autonomy is better treated as a property of the operation than of the agent. An operation qualifies for unattended execution when it is verifiable (its result can be checked mechanically), reversible (there is a known, cheap path back) and contained (its worst case is known in advance and small). We ground the argument in closed-loop systems operators already trust, such as health-check ejection, circuit breakers and Kubernetes controllers. We then describe how the framework is implemented in a working system: a gate that scores each proposed operation from infrastructure facts against a ceiling set by one human-controlled dial, and a separate containment layer whose only output is a pull request. We report no empirical results. We separate implemented mechanisms from hypotheses and identify verifiability, which our own gate does not yet score, as the framework's main open problem.
Related
- A pilot-wellness-informed ecological framework for human-autonomy teaming in future fighter aviation
- THE REFERENCE-AUTONOMY DYNAMICS PRINCIPLE (RADP) A General Theoretical Framework for Reference-Bound Pursuit, Capability-Referenced Autonomy, and Their Complementary Causal Dynamics
- Guarded Autonomy for Satellites: A Policy-Gated AI Agent Framework for Safe Onboard Fault Response
- Data-driven risk assessment framework for railway operation accidents based on an improved Bayesian network
- Guarded Autonomy for Satellites: A Policy-Gated AI Agent Framework for Safe Onboard Fault Response
BibTeX
@misc{dubovskii2026autonomy,
title = {{Autonomy Is a Property of the Operation: A Framework for Deciding What DevOps Agents May Do Unattended}},
author = {Ilia Dubovskii},
howpublished = {Zenodo},
year = {2026},
month = oct,
doi = {10.5281/zenodo.23605208},
url = {https://zenodo.org/records/23605208},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Autonomy Is a Property of the Operation: A Framework for Deciding What DevOps Agents May Do Unattended
AU - Ilia Dubovskii
PY - 2026
DA - 2026/10/23
PB - Zenodo
DO - 10.5281/zenodo.23605208
UR - https://zenodo.org/records/23605208
AB - Automation moved the execution of operational work off engineers but not their attention: someone still has to look, judge and approve, and that person has become the bottleneck. As agents built on large language models widen what a DevOps system can do, deciding what an agent may do without a human looking is now a practical configuration question. We argue that autonomy is better treated as a property of the operation than of the agent. An operation qualifies for unattended execution when it is verifiable (its result can be checked mechanically), reversible (there is a known, cheap path back) and contained (its worst case is known in advance and small). We ground the argument in closed-loop systems operators already trust, such as health-check ejection, circuit breakers and Kubernetes controllers. We then describe how the framework is implemented in a working system: a gate that scores each proposed operation from infrastructure facts against a ceiling set by one human-controlled dial, and a separate containment layer whose only output is a pull request. We report no empirical results. We separate implemented mechanisms from hypotheses and identify verifiability, which our own gate does not yet score, as the framework's main open problem.
ER -