Operationalizing Ethics for AI Agents: How Developers Encode Values into Repository Context Files

TL;DR

This paper explores how developers encode ethical principles into repository files to guide AI agent behavior within software development workflows.

Contribution

It introduces the concept of encoding ethics into repository context files and investigates current practices and implications for AI governance.

Findings

Developers embed guidance on fairness, accessibility, sustainability, tone, and privacy.

Repository files act as a governance layer translating principles into directives.

This practice influences how AI agents behave and are governed in development workflows.

Abstract

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.