Operationalizing Ethics for AI Agents: How Developers Encode Values into Repository Context Files
For AI governance researchers and software engineering practitioners, this paper identifies a nascent practice of operationalizing ethics for AI agents, but it is a vision paper with preliminary findings and no concrete results.
This paper investigates how developers encode ethical principles into repository-level context files (e.g., AGENTS.md) for AI coding agents, finding that guidance related to fairness, accessibility, sustainability, tone, and privacy is already being embedded. The authors propose a research agenda to study this emerging practice, including how values vary across communities and whether agents adhere to constraints.
As AI coding agents become embedded in software development workflows, developers are beginning to operationalize ethical principles by encoding behavioral rules into repository-level context files for AI agents, such as AGENTS.md files. Rather than examining the ethics of AI agents in the abstract, this vision paper investigates how ethics and values are already being translated for AI agents into actionable instructions that shape agent behavior. Through a preliminary investigation, we find that developers are already embedding guidance related to fairness, accessibility, sustainability, tone, and privacy. These artifacts function as a developer-authored governance layer, translating abstract principles into situated, natural-language directives within development workflows. We outline a research agenda for studying this emerging practice, including how encoded values vary across communities, what governance dynamics emerge when multiple contributors negotiate these files, and whether agents reliably adhere to the constraints specified. Understanding how ethics and values are operationalized for AI agents is essential to ground AI governance in modern software engineering practice.