# PromptMN: Pseudo Prompting Language

arXiv: https://arxiv.org/abs/2606.17164 · HTML: https://mlsanity.com/paper/2606.17164/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 49 references that are in the map.
- First posted on arXiv 15 Jun 2026.

## Builds on (most cited first, 10 of 10)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks](https://mlsanity.com/paper/2204.07705/) (2022)
- [How much do language models memorize?](https://mlsanity.com/paper/2505.24832/) (2025)
- [A Survey of Automatic Prompt Engineering: An Optimization Perspective](https://mlsanity.com/paper/2502.11560/) (2025)
- [MEMENTO: Teaching LLMs to Manage Their Own Context](https://mlsanity.com/paper/2604.09852/) (2026)
- [Context Engineering 2.0: The Context of Context Engineering](https://mlsanity.com/paper/2510.26493/) (2025)
- [A Practical Guide for Designing, Developing, and Deploying Production-Grade Agentic AI Workflows](https://mlsanity.com/paper/2512.08769/) (2025)
- [Prompting with Pseudo-Code Instructions](https://mlsanity.com/paper/2305.11790/) (2023)
- [LLM-Based Agentic Systems for Software Engineering: Challenges and Opportunities](https://mlsanity.com/paper/2601.09822/) (2026)
- [Training with Pseudo-Code for Instruction Following](https://mlsanity.com/paper/2505.18011/) (2025)

## Abstract (arXiv)

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.