Town of Nettetal gives its 580 employees AI chatbots through a hybrid three-zone model with an in-house green zone on its own GPU servers
Nettetal's IT service began building a green zone in 2024 on its own GPU servers with open-source LLMs including Qwen 32B, so prompts, data and results stay in-house, including confidential and social data. A yellow zone runs Mistral and Qwen on T-Systems' sovereign T Cloud Public, and a red zone gives token-billed access to GPT, Claude and Gemini models without confidential data. RAG combines internal data for IT support, research and urban planning; the town received the Digital Award in Bronze at KOMMUNALE in November 2025.
Overview
Nettetal's IT service began building a green zone in 2024 on its own GPU servers with open-source LLMs including Qwen 32B, so prompts, data and results stay in-house, including confidential and social data. A yellow zone runs Mistral and Qwen on T-Systems' sovereign T Cloud Public, and a red zone gives token-billed access to GPT, Claude and Gemini models without confidential data. RAG combines internal data for IT support, research and urban planning; the town received the Digital Award in Bronze at KOMMUNALE in November 2025.
This entry has 13 published fields tied to exact passages in an immutable source capture.
Inspect the highlighted sourceThe challenge
Nettetal faces a shortage of skilled workers in public administration, with a large proportion of employees retiring by 2030, and wanted to give all employees an AI chatbot that supports daily work while meeting all data protection requirements, including for confidential, personal and social data.
The solution
Nettetal introduced a hybrid 3-zone AI model: a green zone on its own GPU servers with open-source LLMs including Qwen 32B where all prompts, data and results remain in-house; a yellow zone using Mistral and Qwen on the sovereign T Cloud Public for personal data; and a red zone giving token-billed access to GPT, Claude and Gemini models without confidential data. Retrieval Augmented Generation (RAG) combines internal data with external models for IT support, research and urban planning.
Reported business value
The source says the solution combines security and flexibility, increases productivity, reduces costs and ensures transparent token-based billing, without giving figures. The town received the Digital Award in Bronze at the KOMMUNALE trade fair in November 2025.
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.
Estonia 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.
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.
Was this helpful?
Your feedback helps us improve our use case database
