Saved in:
Bibliographic Details
Main Authors: Gupta, Vatsal, Sreenivasamurthy, Darshan
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.15799
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911520856735744
author Gupta, Vatsal
Sreenivasamurthy, Darshan
author_facet Gupta, Vatsal
Sreenivasamurthy, Darshan
contents Prose2Policy (P2P) is a LLM-based practical tool that translates natural-language access control policies (NLACPs) into executable Rego code (the policy language of Open Policy Agent, OPA). It provides a modular, end-to-end pipeline that performs policy detection, component extraction, schema validation, linting, compilation, automatic test generation and execution. Prose2Policy is designed to bridge the gap between human-readable access requirements and machine-enforceable policy-as-code (PaC) while emphasizing deployment reliability and auditability. We evaluated Prose2Policy on the ACRE dataset and demonstrated a 95.3\% compile rate for accepted policies, with automated testing achieving a 82.2\% positive-test pass rate and a 98.9\% negative-test pass rate. These results indicate that Prose2Policy produces syntactically robust and behaviorally consistent Rego policies suitable for Zero Trust and compliance-driven environments.
format Preprint
id arxiv_https___arxiv_org_abs_2603_15799
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Prose2Policy (P2P): A Practical LLM Pipeline for Translating Natural-Language Access Policies into Executable Rego
Gupta, Vatsal
Sreenivasamurthy, Darshan
Artificial Intelligence
Prose2Policy (P2P) is a LLM-based practical tool that translates natural-language access control policies (NLACPs) into executable Rego code (the policy language of Open Policy Agent, OPA). It provides a modular, end-to-end pipeline that performs policy detection, component extraction, schema validation, linting, compilation, automatic test generation and execution. Prose2Policy is designed to bridge the gap between human-readable access requirements and machine-enforceable policy-as-code (PaC) while emphasizing deployment reliability and auditability. We evaluated Prose2Policy on the ACRE dataset and demonstrated a 95.3\% compile rate for accepted policies, with automated testing achieving a 82.2\% positive-test pass rate and a 98.9\% negative-test pass rate. These results indicate that Prose2Policy produces syntactically robust and behaviorally consistent Rego policies suitable for Zero Trust and compliance-driven environments.
title Prose2Policy (P2P): A Practical LLM Pipeline for Translating Natural-Language Access Policies into Executable Rego
topic Artificial Intelligence
url https://arxiv.org/abs/2603.15799