{"slug":"stadtverwaltung-n-rnberg-pilots-ai-chatbots-an-llm-completeness-check-for-housing-benefit-applications-and-document-recognition-for-birth-registers","url":"https://findausecase.com/use-cases/stadtverwaltung-n-rnberg-pilots-ai-chatbots-an-llm-completeness-check-for-housing-benefit-applications-and-document-recognition-for-birth-registers","title":"Stadtverwaltung Nürnberg pilots AI chatbots, an LLM completeness check for housing-benefit applications and document recognition for birth registers","description":"The City of Nuremberg's digitalisation office reports on its AI pilots: a chatbot in the social and youth office (more than 10,000 users and over 25,000 messages from July to December 2024), an LLM assistant that checked 100 housing-benefit (Wohngeld) applications for missing evidence from August to December 2024, a pilot on intelligent document processing for birth registers (about 215,000 records from 1974 to 2007 are to be digitised; the system has been trained on over 200 documents since October 2024), and a feedback classification pilot that analysed about 3,500 records. The report states relief effects cannot yet be quantified.","company":"Stadt Nürnberg","industry":"Government & Public Sector","aiCapabilities":["Conversational AI","Document Intelligence","Large Language Models","Natural Language Processing"],"technology":["ChatGPT","Robotic Process Automation"],"deployment":"Unknown","problemStatement":"The Wohngeld reform of 2023 greatly increased application volumes, and together with a shortage of skilled staff this leads to longer processing times. The city also has to digitise about 215,000 birth records from 1974 to 2007, which requires a very high personnel and time effort, and wants to relieve service phones and analyse several thousand free-text citizen feedback items more efficiently.","solutionApproach":"The digitalisation office runs four pilots: a chatbot in the social and youth office using self-maintained knowledge bases and falling back on ChatGPT for assigned internet sources; an LLM-based assistant that reads online housing-benefit applications, lists missing evidence and drafts request letters; intelligent document processing combined with robotic process automation to read printed and handwritten text from scanned birth registers; and neural networks built on pretrained models that classify citizen feedback texts.","businessValue":"The report states that relief effects cannot yet be quantified for lack of comparison data. The chatbot had more than 10,000 users and over 25,000 messages from July to December 2024, and 100 housing-benefit applications were successfully checked by the LLM from August to December 2024, with first results showing high quality. About 3,500 feedback records were analysed. The birth-register system is still being trained on over 200 documents. The report describes these as pilots; a productive solution is only planned for the housing-benefit check.","evidence":{"band":"high"},"sourceUrl":"https://www.nuernberg.de/imperia/md/digitales_nuernberg/dokumente/dip_004_2025_sachverhaltsdarstellung__1_.pdf","dates":{"publishedAt":"2026-10-19T05:48:50.717Z","publishedAtSource":"pipeline","updatedAt":"2026-10-19T05:48:50.717Z"},"license":"Open for reading and citing with a link to https://findausecase.com/use-cases/stadtverwaltung-n-rnberg-pilots-ai-chatbots-an-llm-completeness-check-for-housing-benefit-applications-and-document-recognition-for-birth-registers. Bulk republication requires permission."}