A Natural Language Interface for Building Business Automation Decision Rules

Abstract

We propose an NL paradigm and platform for the construction of business automation rules that incorporate a constrained natural language (CNL) – a domain-specific highly consumable language to validate and review synthesized code. Our approach utilizes LLMs to translate business rules described in NL into CNL for human review which can then be transpiled into the business automation code of the rule engine. To address challenges in the translation from NL to CNL, we utilize several techniques such as constrained decoding, fine-tuning and prompt engineering.