Generative Agents at Work: Redesigning Administrative Processes at the German Federal Employment Agency

Proceedings of the ... Annual Hawaii International Conference on System Sciences/Proceedings of the Annual Hawaii International Conference on System Sciences

Abstract

The integration of Generative Artificial Intelligence (GenAI) in public administration offers new ways to handle service and technology complexity while meeting high standards. This paper presents a case study from the German Federal Employment Agency, where a multi-agent system using local large language models (LLMs) automates the conversion of information technology (IT) change requests into structured IT development tasks (Jira tickets). Specialized agents interpret requirements, break them into tasks, and generate consistent entries. This improves organizational efficiency, reduces routine work, and outperforms traditional automation by enabling context-aware reasoning and dialogue, all within a secure, on-premise environment. While motivated by Germany’s demographic challenges, the findings have global relevance for public sector modernization and automation.

Authors 6

1. Alina M. Chircu

   University of New Mexico

   Affiliation as printed

   University of New Mexico , USA

2. Christian Czarnecki Aachen

   FH Aachen

   Affiliation as printed

   Eldar Sultanow Capgemini , Germany

   FH Aachen , Germany

3. Tim Neumüller
4. Sebastian Sebrak
   Affiliation as printed

   Capgemini , Germany

5. Eldar Sultanow
6. Florian Winzer

   Federal Employment Agency

   Affiliation as printed

   Federal Employment Agency , Germany

   Tim Neumüller Capgemini , Germany