Core Concepts
ProMoAI leverages Large Language Models to automate process model generation, optimization, and refinement, simplifying complex workflows for non-experts.
Abstract
1. Abstract:
- ProMoAI uses Large Language Models (LLMs) for automatic process model generation from text.
- Incorporates prompt engineering, error handling, and code generation techniques.
- Supports user feedback for refining process models.
2. Introduction:
- Traditional process modeling requires expertise and specialized knowledge.
- LLMs have shown advancements in understanding and generating human-like text.
3. Application Domain:
- ProMoAI benefits business process management, workflow automation, and systems engineering.
- Enables rapid prototyping and visualization of workflows.
4. System Overview:
- Utilizes Partially Ordered Workflow Language (POWL) for process model generation.
- Employs prompt engineering techniques to guide LLM in accurate process model generation.
- Implements secure execution environment for generating valid process models.
5. Future Work and Extensions:
- Designed to be forward-compatible with newer LLM models.
- Plans to support additional LLMs beyond OpenAI.
6. Example Application:
- Applied ProMoAI with GPT-4 for an online shop process model.
- Utilizes POWL to model complex non-hierarchical dependencies.
7. Conclusion:
- ProMoAI simplifies process modeling by translating natural language descriptions into formal process models.
- Enhances organizational workflow optimization through AI-driven automation.
Stats
ProMoAI utilizes Large Language Models (LLMs) for process model generation.
Currently supports OpenAI LLMs.
Plans to support more LLMs in the future.
Quotes
"ProMoAI simplifies the creation of complex process models, opening up new possibilities for optimizing organizational workflows."
"LLMs have demonstrated strong capabilities in solving programming tasks and generating executable code."