Policy-as-Prompt: Turning AI Governance Rules into Guardrails for AI Agents
This addresses the need for scalable AI safety and compliance in regulated settings, though it appears incremental as an application of policy-as-code to AI agents.
The paper tackles the problem of enforcing AI governance rules in autonomous agents by introducing a framework that converts unstructured design artifacts into verifiable runtime guardrails, reducing prompt-injection risk and blocking out-of-scope requests.
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.