Large Language Model (LLM) agents hold promise for a flexible and scalable alternative to traditional business process automation, but struggle to reliably follow complex company policies. In this study we introduce a deterministic, transparent, and modular framework for enforcing business policy adherence in agentic workflows. Our method operates in two phases: (1) an offline buildtime stage that compiles policy documents into verifiable guard code associated with tool use, and (2) a runtime integration where these guards ensure compliance before each agent action. We demonstrate our approach on the challenging τ-bench Airlines domain, showing encouraging preliminary results in policy enforcement, and further outline key challenges for real-world deployments.
@article{arxiv.2507.16459,
title = {Towards Enforcing Company Policy Adherence in Agentic Workflows},
author = {Naama Zwerdling and David Boaz and Ella Rabinovich and Guy Uziel and David Amid and Ateret Anaby-Tavor},
journal= {arXiv preprint arXiv:2507.16459},
year = {2025}
}