Deliberate pacing balances human oversight and autonomous software development

Deliberate Pacing for Human Oversight in Agentic Software Development

Software Engineering

Summary

Software development is increasingly done by AI agents working on their own. This raises the problem of how and when humans can effectively check the work and make decisions. The authors propose a strategy called deliberate pacing, where the speed and timing of autonomous development are controlled intentionally. This approach aims to keep chances for human oversight meaningful without slowing down development too much or causing extra work. They identify factors like timing of review, cost of human attention, and dependencies across development stages that affect how pacing should be done.

What this means in practice

  • For software development managers: Adjust work schedules to balance AI autonomy and human code reviews for better oversight without slowing progress.
  • For devops teams: Plan intervention points in automated deployment pipelines to enable meaningful checks of agent-generated software changes.

A position paper. It proposes an approach and reports no results.

Authors

Tobias Reichel, Michèle Stassen, Anamaria Mojica-Hanke, Maria Teresa Baldassarre, Sebastian Baltes, Alexander Serebrenik, Steffen Herbold

Abstract

Agentic AI increasingly enables software development activities to proceed without continuous human involvement. While this autonomy may accelerate development, it also raises questions about when developers can meaningfully oversee software development done by agents. We propose deliberate pacing: intentionally adjusting when and how autonomous development proceeds to preserve opportunities for meaningful oversight. Drawing on an exploratory multivocal literature review of 20 sources, we identify three factors motivating this vision: changing relative costs of human involvement, the timing of oversight opportunities, and interdependencies between pacing decisions across the software development life cycle. We argue that neither uninterrupted autonomy nor frequent human intervention is universal. Instead, pacing should balance opportunities to understand and influence consequential decisions against costs in human attention, development time, and rework. We outline a research agenda to investigate when deliberate pacing is beneficial, how intervention timing affects oversight, and how pacing decisions interact across development activities.