When Prompt Engineering Meets Software Engineering: CNL-P as Natural and Robust "APIs'' for Human-AI Interaction

2025-08-09

AI Summary

Natural language (NL) prompts suffer from semantic ambiguity and inconsistent execution when interacting with large language models (LLMs). Method: This paper proposes Controlled Natural Language for Prompting (CNL-P), a structured prompt language inspired by software engineering principles, featuring formal syntax, semantic constraints, and verifiability. It introduces static analysis and syntactic checking into prompt engineering—novel in this domain—by developing an NL→CNL-P automatic transpiler and an integrated linting toolchain. Contribution/Results: CNL-P is formally defined as a new generation of “semantic API” for human-AI interaction, enabling structured prompt modeling, static verification, and execution consistency guarantees. Experiments demonstrate that CNL-P significantly improves LLM response quality, cross-task stability, and prompt reusability, while lowering the barrier to effective prompt engineering and advancing reliable, natural-language–based programming paradigms.

Technology Category

• Natural Language Processing: Prompt Engineering / Prompting
• Machine Learning: Large Multimodal Models (LMMs)
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

With the growing capabilities of large language models (LLMs), they are increasingly applied in areas like intelligent customer service, code generation, and knowledge management. Natural language (NL) prompts act as the ``APIs'' for human-LLM interaction. To improve prompt quality, best practices for prompt engineering (PE) have been developed, including writing guidelines and templates. Building on this, we propose Controlled NL for Prompt (CNL-P), which not only incorporates PE best practices but also draws on key principles from software engineering (SE). CNL-P introduces precise grammar structures and strict semantic norms, further eliminating NL's ambiguity, allowing for a declarative but structured and accurate expression of user intent. This helps LLMs better interpret and execute the prompts, leading to more consistent and higher-quality outputs. We also introduce an NL2CNL-P conversion tool based on LLMs, enabling users to write prompts in NL, which are then transformed into CNL-P format, thus lowering the learning curve of CNL-P. In particular, we develop a linting tool that checks CNL-P prompts for syntactic and semantic accuracy, applying static analysis techniques to NL for the first time. Extensive experiments demonstrate that CNL-P enhances the quality of LLM responses through the novel and organic synergy of PE and SE. We believe that CNL-P can bridge the gap between emerging PE and traditional SE, laying the foundation for a new programming paradigm centered around NL.

Problem

• Reducing ambiguity in natural language prompts for LLMs
• Integrating software engineering principles into prompt design
• Automating conversion and validation of structured prompts

Innovation

• CNL-P combines PE best practices with SE principles
• Introduces precise grammar and strict semantic norms
• NL2CNL-P tool converts natural language to CNL-P