Download PDFOpen PDF in browser

Ritchy – Federated AI Support: Quality Assurance, Architecture, Operations

11 pagesPublished: June 18, 2026

Abstract

We present Ritchy, an AI-powered support chatbot that has been in productive use at the IT Center of RWTH Aachen University since spring 2025. Ritchy combines a large language model (LLM) with retrieval-augmented generation (RAG) grounded in curated documentation synchronized from the knowledge management system Sabio. Based on operational data and an ISO 9001-embedded PDCA process, we show that user feedback alone is too incomplete and sometimes biased to serve as a reliable quality indicator, making continuous human quality assurance essential. From these findings, we derive key requirements for federated deployment—multi-tenancy, local content ownership, and quality assurance as a core function—and propose a reference architecture separating a shared platform layer from the university-specific layer. We further outline three deployment scenarios (all-in-one, fully configurable, and open source) and corresponding cost models.

Keyphrases: ai chatbot, architecture, federated ai support, operation, quality assurance, rag, ritchy, servicedesk

In: Laurence Desnos, Carmen Diaz, Janina Mincer-Daszkiewicz, Lazaros Merakos, Raimund Vogl, Stuart McLellan and Ulrike Lucke (editors). Proceedings of EUNIS 2026 Annual Congress, vol 109, pages 41-51.

BibTeX entry
@inproceedings{EUNIS2026:Ritchy_Federated_AI_Support,
  author    = {Ingo Hengstebeck and Bernd Decker and Sarah Grzemski and Sara Erdem},
  title     = {Ritchy – Federated AI Support: Quality Assurance, Architecture, Operations},
  booktitle = {Proceedings of EUNIS 2026 Annual Congress},
  editor    = {Laurence Desnos and Carmen Diaz and Janina Mincer-Daszkiewicz and Lazaros Merakos and Raimund Vogl and Stuart McLellan and Ulrike Lucke},
  series    = {EPiC Series in Computing},
  volume    = {109},
  publisher = {EasyChair},
  bibsource = {EasyChair, https://easychair.org},
  issn      = {2398-7340},
  url       = {/publications/paper/jKD3},
  doi       = {10.29007/j6sr},
  pages     = {41-51},
  year      = {2026}}
Download PDFOpen PDF in browser