Munich Fire Department tests an AI operator for non-emergency patient transport calls, built on Microsoft Foundry
The Munich Fire Department and Microsoft built a multilingual voice AI operator to take non-emergency patient transport calls from hospitals and nursing homes, using Microsoft Foundry, Azure Speech and Azure AI Search to validate addresses against a municipal database. Human dispatchers stay in the loop and calls hand off to them when the bot does not understand. In beta testing, with broader testing planned at LMU Klinikum.
Overview
The Munich Fire Department and Microsoft built a multilingual voice AI operator to take non-emergency patient transport calls from hospitals and nursing homes, using Microsoft Foundry, Azure Speech and Azure AI Search to validate addresses against a municipal database. Human dispatchers stay in the loop and calls hand off to them when the bot does not understand. In beta testing, with broader testing planned at LMU Klinikum.
This entry has 12 published fields tied to exact passages in an immutable source capture.
Inspect the highlighted sourceThe challenge
Munich Fire Department dispatchers handle emergency calls and also arrange non-emergency patient transports between hospitals or home from nursing homes. The department wanted to relieve pressure on dispatchers, shorten waiting times for hospitals and nursing homes that book transports, and ease the process for health-care workers, many of whom speak German as a second or third language.
The solution
IT experts from the fire department and Microsoft built an AI operator that handles non-emergency transport calls in natural language in several languages. Microsoft Foundry assembles and governs the chatbot, Azure Speech (HD Voice) supplies the voice, and Azure AI Search validates addresses against a municipal database. A human dispatcher takes over immediately if the chatbot does not understand something.
Reported business value
The source reports no measured results. In beta testing, testers have said the AI operator has been very effective and easy to use. The department hopes it can unburden dispatchers of non-emergency calls so they have more time for medical emergencies and fires, and a hospital emergency-ward director hopes it will save nurses' time and could help open hospital beds more quickly by cutting waiting times.
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