Structural Quality Gaps in Practitioner AI Governance Prompts: An Empirical Study Using a Five-Principle Evaluation Framework
This work identifies a previously undocumented structural quality gap in practitioner-authored AI governance prompts, which is relevant for requirements engineering in AI-assisted development.
The authors introduce a five-principle evaluation framework for AI governance prompts and apply it to 34 AGENTS.md files from GitHub, finding that 37% of file-model pairs fall below a structural completeness threshold, with data classification and assessment rubric criteria most frequently missing.
AI governance programmes increasingly rely on natural language prompts to constrain and direct AI agent behaviour. These prompts function as executable specifications: they define the agent's mandate, scope, and quality criteria. Despite this role, no systematic framework exists for evaluating whether a governance prompt is structurally complete. We introduce a five-principle evaluation framework grounded in computability theory, proof theory, and Bayesian epistemology, and apply it to an empirical corpus of 34 publicly available AGENTS.md governance files sourced from GitHub. Our evaluation reveals that 37% of evaluated file-model pairs score below the structural completeness threshold, with data classification and assessment rubric criteria most frequently absent. These results suggest that practitioner-authored governance prompts exhibit consistent structural patterns that automated static analysis could detect and remediate. We discuss implications for requirements engineering practice in AI-assisted development contexts, identify a previously undocumented artefact classification gap in the AGENTS.md convention, and propose directions for tool support.