Policy-as-Prompt: Turning AI Governance Rules into Guardrails for AI Agents

As autonomous AI agents are used in regulated and safety-critical settings, organizations need effective ways to turn policy into enforceable controls. We introduce a regulatory machine learning framework that converts unstructured design artifacts (like PRDs, TDDs, and code) into verifiable runtime guardrails. Our Policy as Prompt method reads these documents and risk controls to build a source-linked policy tree. This tree is then compiled into lightweight, prompt-based classifiers for real-time runtime monitoring. The system is built to enforce least privilege and data minimization. For conformity assessment, it provides complete provenance, traceability, and audit logging, all integrated with a human-in-the-loop review process. Evaluations show our system reduces prompt-injection risk, blocks out-of-scope requests, and limits toxic outputs. It also generates auditable rationales aligned with AI governance frameworks. By treating policies as executable prompts (a policy-as-code for agents), this approach enables secure-by-design deployment, continuous compliance, and scalable AI safety and AI security assurance for regulatable ML.

Key Contributions

Policy-as-Prompt pipeline that automatically extracts security constraints from unstructured development artifacts (PRDs, TDDs, code) and builds a source-linked policy tree
Compilation of verified policy trees into lightweight prompt-based classifiers that act as real-time 'judge' LLMs enforcing least-privilege at agent input/output boundaries
End-to-end audit framework providing provenance, traceability, and human-in-the-loop review aligned with EU AI Act, NIST AI RMF, and ISO/IEC 42001