Enterprise Resource Planning systems provide a wide range of functionalities to support employees in their daily work. These systems integrate data and processes across departments such as procurement, finance, logistics, and human resources. In theory, ERP systems enable employees to access relevant information, perform transactions, and coordinate organizational activities efficiently within a single platform.

In practice, however, many employees only use a small fraction of the available system capabilities. One reason for this is that ERP systems are often perceived as complex and difficult to navigate. Users may not know where specific information is stored, which functions are available, or how certain tasks can be performed within the system. As a result, employees frequently rely on workarounds, additional communication with colleagues, or manual searches instead of leveraging the full capabilities of the ERP system.

Recent advances in conversational AI and large language models offer new opportunities to simplify how users interact with complex software systems. Instead of navigating menus and interfaces, employees could interact with enterprise systems through natural language, asking questions such as “Which purchase orders require approval today?” or “Show me the most recent customer orders.” Such conversational interfaces could significantly improve system accessibility and user experience.

Within the Process Innovation and Automation Lab, an instance of the open source ERP system ERPNext has been deployed to simulate and study digital business processes. This project aims to explore how a conversational chatbot interface can be connected to ERPNext, enabling users to query and interact with the system through natural language. The resulting prototype should demonstrate how conversational interfaces can enhance accessibility and usability of enterprise systems. In addition, the project will explore how the potential benefits of conversational ERP interaction can be systematically evaluated and which evaluation criteria are suitable to assess the impact of such interfaces in practice.

The goal of this project is to design and implement a prototype chatbot that enables natural language interaction with an ERPNext system.

Key objectives include:

1. Analyze typical user information needs and interactions within ERP systems to identify relevant use cases for conversational access.
2. Design an architecture that connects a conversational AI interface with ERPNext using available APIs and system integrations.
3. Develop a chatbot prototype that allows users to query ERP data and retrieve relevant information through natural language interaction.
4. Implement selected example scenarios (for example retrieving orders, approvals, or system information) within the ERPNext environment.
5. Develop an evaluation approach to assess the usability and potential benefits of conversational ERP interaction and apply it to the developed prototype.

The final outcome should be a functional prototype illustrating how conversational interfaces can improve interaction with enterprise systems.

References

• Anthropic (Hg.) (2024): Building Effective AI Agents \ Anthropic. www.anthropic.com/engineering/building-effective-agents, z
• Davenport, T. H. (1998): Putting the enterprise into the enterprise system. In: Harvard business review 76 (4), S. 121–131.
• ERPNext Documentation (2026). docs.erpnext.com/homepage
• Mariani, Marcello M.; Hashemi, Novin; Wirtz, Jochen (2023): Artificial intelligence empowered conversational agents: A systematic literature review and research agenda. In: Journal of Business Research 161, S. 113838. DOI: 10.1016/j.jbusres.2023.113838.
• Shunyu Yao; Dian Yu; Jeffrey Zhao; Izhak Shafran; Thomas L. Griffiths; Yuan Cao; Karthik Narasimhan (2023): Tree of Thoughts: Deliberate Problem Solving with Large Language Models. In: Advances in Neural Information Processing Systems 36 - 37th Conference on Neural Information Processing collaborate.princeton.edu/en/publications/tree-of-thoughts-deliberate-problem-solving-with-large-language-m-2/

Project Requirements

• Development of a project plan and distribution of tasks among group members
• Analysis of ERPNext APIs and system interaction possibilities
• Design of an architecture connecting a chatbot interface with ERPNext
• Development of a working prototype for conversational interaction with ERP data
• Documentation of system architecture and implemented features
• Presentation of intermediate and final results

Prerequisites

• Students of Information Systems, Computer Science, or Software Engineering at bachelor or master level
• Interest in artificial intelligence, conversational systems, and enterprise software
• Basic programming skills (for example Python, JavaScript, or similar)
• Motivation to experiment with system integrations and open source technologies

If you are interested in this porject, follow the steps below to submit your application.

1. Form a project group
Projects are typically carried out in groups of 3–5 students. We recommend forming a group with fellow students before applying.

2. Prepare your application
Send a short application including:

• your transcript of records
• a short motivation letter (about one page) explaining why your group is interested in the project.

3. Submit your application
Send your application via email to:jannis.nacke (at) icb.uni-due.de