Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

ProMoAI: Process Modeling with Generative AI

Humam Kourani, Alessandro Berti, Daniel Schuster, Wil M. P. van der Aalst

TL;DR

ProMoAI tackles the challenge of making process modeling accessible by using large language models to translate natural-language descriptions into formal representations. It combines POWL-based generation with secure code execution, robust error handling, and an interactive refinement loop to iteratively improve models. The approach supports exports to BPMN and PNML and enables rapid domain-specific prototyping. This work advances AI-assisted process modeling by reducing expert barriers and enabling real-time optimization of organizational workflows.

Abstract

ProMoAI is a novel tool that leverages Large Language Models (LLMs) to automatically generate process models from textual descriptions, incorporating advanced prompt engineering, error handling, and code generation techniques. Beyond automating the generation of complex process models, ProMoAI also supports process model optimization. Users can interact with the tool by providing feedback on the generated model, which is then used for refining the process model. ProMoAI utilizes the capabilities LLMs to offer a novel, AI-driven approach to process modeling, significantly reducing the barrier to entry for users without deep technical knowledge in process modeling.

ProMoAI: Process Modeling with Generative AI

TL;DR

ProMoAI tackles the challenge of making process modeling accessible by using large language models to translate natural-language descriptions into formal representations. It combines POWL-based generation with secure code execution, robust error handling, and an interactive refinement loop to iteratively improve models. The approach supports exports to BPMN and PNML and enables rapid domain-specific prototyping. This work advances AI-assisted process modeling by reducing expert barriers and enabling real-time optimization of organizational workflows.

Abstract

ProMoAI is a novel tool that leverages Large Language Models (LLMs) to automatically generate process models from textual descriptions, incorporating advanced prompt engineering, error handling, and code generation techniques. Beyond automating the generation of complex process models, ProMoAI also supports process model optimization. Users can interact with the tool by providing feedback on the generated model, which is then used for refining the process model. ProMoAI utilizes the capabilities LLMs to offer a novel, AI-driven approach to process modeling, significantly reducing the barrier to entry for users without deep technical knowledge in process modeling.
Paper Structure (12 sections, 3 figures)

This paper contains 12 sections, 3 figures.

Table of Contents

  1. Introduction
  2. Application Domain
  3. Related Work
  4. System Overview
  5. Utilization of POWL
  6. Prompt Engineering Techniques
  7. Process Model Generation
  8. Error Handling
  9. Process Model Refinement
  10. Future Work and Extensions
  11. Example Application
  12. Conclusion

Figures (3)

  • Figure 1: A screenshot of ProMoAI.
  • Figure 2: System architecture.
  • Figure 3: BPMN generated by ProMoAI for the order process using GPT-4. This model conforms to the reference model of the process, and it additionally captures the feedback requests for modeling the item selection as a loop and allowing for skipping the reward selection.