The paper maps three structural requirements from DO-178C and DO-330 onto AI governance, defining epoch limits and proof surfaces while noting their absence in current AI instruments.
Structural Quality Gaps in Practitioner AI Governance Prompts: An Empirical Study Using a Five-Principle Evaluation Framework
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
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.
fields
cs.SE 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Fifty Years of Specification Completeness: What Aviation Certification Tells AI Governance About Epoch Limits, Proof Surfaces, and the Structural Gap
The paper maps three structural requirements from DO-178C and DO-330 onto AI governance, defining epoch limits and proof surfaces while noting their absence in current AI instruments.