PromptMN: Pseudo Prompting Language
Quick Answer
PromptMN is a pseudo-prompting domain-specific language that enhances human-AI interaction by annotating natural language with structured directives.
Quick Take
PromptMN is a pseudo-prompting domain-specific language that enhances human-AI interaction by annotating natural language with structured directives. Tested on models like Claude Fable 5 and GPT-5.5, it effectively resolves complex instructions without fine-tuning, aiming to reduce ambiguity in software development workflows.
Key Points
- Introduces compact, %-prefixed directives for roles, goals, and constraints.
- Evaluated on models including Claude Fable 5 and GPT-5.5 with successful instruction resolution.
- Supports complex structures like conditionals and repetition without fine-tuning.
- Aims to reduce repair cycles in software development by clarifying human-to-AI interactions.
- Facilitates reverse prompt engineering for better alignment of user expectations.
Paper Resources
Article Content
From source RSS / original summaryarXiv:2606. 17164v1 Announce Type: new 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.
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). 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'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.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CL
See more →Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents?
The REFLECT benchmark reveals that current LLM judges are unreliable, achieving below 55% accuracy in evaluating reasoning and evidence use, highlighting the need for improved evaluation methods for deep research agents.