ARPaCCino: An Agentic-RAG for Policy as Code Compliance

TL;DR

ARPaCCino is an innovative system that leverages Large Language Models, Retrieval-Augmented-Generation, and tool-based validation to automate and improve Policy as Code compliance in Infrastructure as Code environments, addressing complexity and misconfiguration issues.

Contribution

It introduces a modular agentic architecture combining LLMs, RAG, and validation tools for automated policy generation and verification across diverse IaC frameworks.

Findings

Effectively generates correct Rego policies from natural language.

Identifies non-compliance in IaC configurations.

Successfully applies corrections even with smaller LLMs.

Abstract

Policy as Code (PaC) is a paradigm that encodes security and compliance policies into machine-readable formats, enabling automated enforcement in Infrastructure as Code (IaC) environments. However, its adoption is hindered by the complexity of policy languages and the risk of misconfigurations. In this work, we present ARPaCCino, an agentic system that combines Large Language Models (LLMs), Retrieval-Augmented-Generation (RAG), and tool-based validation to automate the generation and verification of PaC rules. Given natural language descriptions of the desired policies, ARPaCCino generates formal Rego rules, assesses IaC compliance, and iteratively refines the IaC configurations to ensure conformance. Thanks to its modular agentic architecture and integration with external tools and knowledge bases, ARPaCCino supports policy validation across a wide range of technologies, including niche or emerging IaC frameworks. Experimental evaluation involving a Terraform-based case study demonstrates ARPaCCino's effectiveness in generating syntactically and semantically correct policies, identifying non-compliant infrastructures, and applying corrective modifications, even when using smaller, open-weight LLMs. Our results highlight the potential of agentic RAG architectures to enhance the automation, reliability, and accessibility of PaC workflows.