Stadtverwaltung Nürnberg pilots AI chatbots, an LLM completeness check for housing-benefit applications and document recognition for birth registers
Stadt NürnbergChatGPT · Robotic Process AutomationThe 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.
Overview
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.
This entry has 13 published fields tied to exact passages in an immutable source capture.
Inspect the highlighted sourceThe challenge
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.
The solution
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.
Reported business value
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.
Sources
Open any source and check the claim yourself — that is the point of the register.
This record was researched and written with AI assistance, and its claims were checked against the sources above. (EU AI Act art. 50 transparency notice.)
Other government & public sector entries in the register.
GovTech unlocks data insights to improve nationwide services with Databricks
Singapore's Government Technology Agency (GovTech) migrated from an on-premises dashboarding system to the Databricks Data + AI Platform on AWS with Unity Catalog and Delta Lake, cutting dashboard creation time from 90 to 30 days, democratizing data across 50% of corporate divisions in the first year, and saving 8,000 labor hours annually.
GovTech· SingaporeDelta Lake · Lakeflow Connect · Lakeflow Jobs +1Estonia rolls out Bürokratt, an AI-guided virtual assistant network for public services
Bürokratt is a network of chatbots deployed on Estonian public sector institutions' websites, letting people obtain information from institutions and use public and information services via virtual assistants. It is a state-created, AI-based digital assistant that helps institutions deliver modern, efficient, around-the-clock customer service using large language models.
City of Helsinki pilots watsonx.ai for multilingual customer care chatbot translation
The City of Helsinki collaborated with IBM Client Engineering and IBM Consulting on a Proof of Value testing whether IBM watsonx.ai could translate foreign-language questions into Finnish for its customer care chatbot, which supports Finnish, English, and Swedish. Watsonx.ai scored 0.90 on the COMET machine-translation metric for English-to-Finnish translation (versus 0.91 for the incumbent system) and 0.87 for Swedish-to-Finnish (versus 0.86), performing on par with the city's existing translation solution.
City of Helsinki· FinlandIBM watsonx.ai
Madrid builds VisitMadridGPT on Azure OpenAI to answer tourists in 95+ languages
The City of Madrid, with partner iUrban, built the VisitMadridGPT virtual assistant on Microsoft Azure OpenAI Service to give tourists accurate, real-time, personalized information in more than 95 languages, drawing from the city's official tourism content. Users average 2.8 questions and spend about 4 minutes 18 seconds per session with a low bounce rate, and the city analyzes assistant conversations to identify popular topics and refine its digital marketing strategy.
Madrid Destino / Madrid City Council· SpainAzure OpenAI ServiceWas this helpful?
Your feedback helps us improve our use case database