Dila builds Aria and Signale IA, in-house AI tools for answering users' questions and processing parliamentary amendments
France's direction de l'information légale et administrative (Dila) built Aria, an assistant based on its own documentary resources and data used by about fifty agents at its Metz site answering Service-public users, and Signale IA, launched in October 2025, which detects duplicate amendments, generates summaries and retrieves earlier briefing sheets. During the PLF 2026 examination about 1,600 agents read and processed over 17,000 amendments with it; the source says it reduces hours or days of manual work to minutes.
Overview
France's direction de l'information légale et administrative (Dila) built Aria, an assistant based on its own documentary resources and data used by about fifty agents at its Metz site answering Service-public users, and Signale IA, launched in October 2025, which detects duplicate amendments, generates summaries and retrieves earlier briefing sheets. During the PLF 2026 examination about 1,600 agents read and processed over 17,000 amendments with it; the source says it reduces hours or days of manual work to minutes.
This entry has 11 published fields tied to exact passages in an immutable source capture.
Inspect the highlighted sourceThe challenge
Dila wanted AI tools tied to specific business needs: Aria to support agents answering Service-public users, and Signale IA to relieve ministerial agents of the heavy, time-consuming sorting of amendments when preparing briefing sheets for deputies.
The solution
Aria is an assistant based on Dila's own documentary resources and data, used by about fifty agents at the Metz site who provide information to Service-public users. Signale IA, launched in October 2025, detects duplicate amendments, generates summaries and retrieves earlier briefing sheets on similar bills, drawing on large language models.
Reported business value
The source reports that Signale IA cuts amendment work from hours or even days of manual effort to minutes depending on volume, and that about 1,600 agents read and processed over 17,000 amendments with it during the PLF 2026 examination; Dila's IT director says Aria brings a much better quality level than generalist assistants.
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
