PromptMN: Pseudo Prompting Language

PromptMN：伪提示语言

Abstract: Prompting has become the primary interface between humans and generative AI, yet many natural language prompts remain fragile: roles, goals, constraints, and expected outputs are often buried in prose or left implicit. In agentic and software development workflows, a misread at the first handoff can propagate through every step, since a significant portion of agent failures stem from context ambiguities rather than model limitations.

摘要： 提示词（Prompting）已成为人类与生成式 AI 之间的主要交互界面，但许多自然语言提示词仍然非常脆弱：角色、目标、约束条件和预期输出往往被淹没在冗长的叙述中，或者处于隐性状态。在智能体（Agentic）和软件开发工作流中，首次交接时的误读可能会蔓延至后续的每一个步骤，因为很大一部分智能体故障并非源于模型本身的局限性，而是源于上下文的歧义。

This paper introduces PromptMN, a pseudo-prompting domain-specific language that annotates natural language with compact, %-prefixed typed directives covering roles, goals, requirements, priorities, constraints, plans, inputs, and outputs. Semantic resolution lets authors write in any order while the model interprets directives by function. PromptMN sits between informal prompting and programming-style pseudocode: structured enough to be inspectable and reusable, yet lightweight enough for analysts, managers, developers, and stakeholders across the software development lifecycle (SDLC).

本文介绍了 PromptMN，这是一种伪提示领域特定语言（DSL）。它通过以 % 为前缀的紧凑型类型化指令来标注自然语言，涵盖了角色、目标、需求、优先级、约束、计划、输入和输出等要素。语义解析功能允许作者以任意顺序编写内容，而模型则会根据功能对指令进行解读。PromptMN 介于非正式提示词与编程风格的伪代码之间：它既具备足够的结构性，便于检查和复用，又足够轻量，适合软件开发生命周期（SDLC）中的分析师、经理、开发人员及相关利益方使用。

PromptMN also pairs with reverse prompt engineering. Asking a model to restate a desired outcome as PromptMN lets users inspect the inferred roles, goals, constraints, and missing assumptions before acting, reducing repair cycles and yielding a reusable artifact for aligning people and AI tools.

PromptMN 还可以与反向提示工程（Reverse Prompt Engineering）结合使用。通过要求模型将预期的结果重述为 PromptMN 格式，用户可以在采取行动前检查模型推断出的角色、目标、约束和缺失的假设，从而减少修复周期，并产出一种可复用的工件，用于协调人类与 AI 工具之间的预期。

PromptMN’s feasibility is evaluated across several frontier models, including Claude Fable 5, Claude Opus 4.8, Gemini 3.1 Pro, and GPT-5.5. The models correctly resolved PromptMN instructions, including complex structures such as repetition, conditionals, methods, and a prime-checking task, without fine-tuning. The same vocabulary applies across new codebases, maintenance, and redesign in the SDLC scenarios presented. While large-scale validation remains future work, these early results suggest PromptMN is a practical step toward clearer, more reviewable human-to-AI interaction.

PromptMN 的可行性已在多个前沿模型上进行了评估，包括 Claude Fable 5、Claude Opus 4.8、Gemini 3.1 Pro 和 GPT-5.5。这些模型在无需微调的情况下，均能正确解析 PromptMN 指令，包括重复、条件判断、方法调用以及素数检查任务等复杂结构。在所展示的 SDLC 场景中，相同的词汇表同样适用于新代码库、维护和重新设计等工作。尽管大规模验证仍有待未来进一步开展，但这些初步结果表明，PromptMN 是实现更清晰、更具可审查性的人机交互迈出的务实一步。