Finnish authority builds AI-apuri, a RAG chatbot platform where civil servants create team chatbots, with 12 chatbots in production
A Finnish authority introduced AI-apuri, a commercial platform on which civil servants build retrieval-augmented chatbots for their own teams, with inference residency controlled and training data capture not permitted. The source reports 12 chatbots in production and over 60 explored use cases, with estimated savings of about 30 minutes per drafted reply and up to 15 minutes per consumer complaint translated and formalised. A human reviews every final communication.
Overview
A Finnish authority introduced AI-apuri, a commercial platform on which civil servants build retrieval-augmented chatbots for their own teams, with inference residency controlled and training data capture not permitted. The source reports 12 chatbots in production and over 60 explored use cases, with estimated savings of about 30 minutes per drafted reply and up to 15 minutes per consumer complaint translated and formalised. A human reviews every final communication.
This entry has 12 published fields tied to exact passages in an immutable source capture.
Inspect the highlighted sourceThe challenge
Generic large language models answer from general training data and cannot reliably rely on curated, task-specific information, while many work processes at the authority require up-to-date internal guidance, legal interpretations and structured external sources.
The solution
AI-apuri is a commercial platform that uses a retrieval-augmented generation architecture, where chatbots retrieve answers from defined internal and external data sources. Civil servants build chatbots for their own teams with support from the ICT unit, can instruct them to answer only from curated sources, and a human reviews and sends the final communication. Inference residency is controlled and training data capture is not permitted.
Reported business value
The source reports 12 chatbots in production and over 60 explored use cases. It says drafting a reply may save about 30 minutes per case and translating and formalising a consumer complaint up to 15 minutes; impact is measured through usage data, funnel progression and case-level time saving estimates.
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
