bol Behörden Online Systemhaus builds FINO, an agentic AI assistant on Amazon Bedrock for city dog tax registration
German public-sector software provider bol built FINO on Amazon Bedrock and Bedrock AgentCore to help citizens submit government forms online, with knowledge-base answers, translation and dog-breed image recognition. Workloads run in the AWS Frankfurt Region for data sovereignty. Source reports more than 90 percent breed identification accuracy and a 5-second average response time in the pilot.
Overview
German public-sector software provider bol built FINO on Amazon Bedrock and Bedrock AgentCore to help citizens submit government forms online, with knowledge-base answers, translation and dog-breed image recognition. Workloads run in the AWS Frankfurt Region for data sovereignty. Source reports more than 90 percent breed identification accuracy and a 5-second average response time in the pilot.
This entry has 14 published fields tied to exact passages in an immutable source capture.
Inspect the highlighted sourceThe challenge
Local municipalities aim to improve public services while addressing budgetary restraints and talent shortages. bol saw an opportunity to reduce the administrative burden of processing and submitting government forms online, while complying with data sovereignty regulations when integrating large language models.
The solution
bol built FINO, an AI assistant that helps citizens submit government forms online, using Amazon Bedrock and Amazon Bedrock AgentCore. FINO answers questions by retrieving data from the city's knowledge base, guides citizens through follow-up steps, and uses AI image recognition on a dog's photo to identify the breed and add it to the registration form. Workloads run in the AWS Frankfurt Region.
Reported business value
In the pilot with a city administration, FINO identifies breeds with more than 90 percent accuracy and an average response time of 5 seconds. bol says that by validating that a form is complete, FINO reduces the need for human intervention and follow-ups, saving time and minimizing errors.
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
