Région Sud deploys an Azure OpenAI and Mistral-based chatbot to help call-centre agents at Allo Région
The Southern Region of France is deploying 22 AI use cases with Microsoft, including a chatbot based on Azure OpenAI Service and Mistral AI models on Azure that assists agents at its Allo Région call centre in answering citizens' queries. It has also automated verification of 30,000 jobseeker training-grant documents a year, and about 20 employees are testing Microsoft 365 Copilot.
Overview
The Southern Region of France is deploying 22 AI use cases with Microsoft, including a chatbot based on Azure OpenAI Service and Mistral AI models on Azure that assists agents at its Allo Région call centre in answering citizens' queries. It has also automated verification of 30,000 jobseeker training-grant documents a year, and about 20 employees are testing Microsoft 365 Copilot.
This entry has 12 published fields tied to exact passages in an immutable source capture.
Inspect the highlighted sourceThe challenge
Région Sud wants to use AI to improve the quality of its public service, including helping call-centre agents respond more effectively to citizens' queries; the source notes that this administration receives 75,000 requests every year.
The solution
A chatbot based on Azure OpenAI Service and Mistral AI models on Azure assists agents at the Allo Région call centre. According to the source, the tool operates in a secure environment and performs queries within the Region's databases. The Region has also automated verification of documents for jobseekers' skill training grants, and about 20 employees are testing Microsoft 365 Copilot.
Reported business value
The source says the Region's agents are able to provide more relevant responses, and that 30,000 grant-verification documents per year are now processed by the machine. The source reports initial results as promising and does not quantify the chatbot's impact.
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
