Normalized claim
Accuracy: 90%
Breed identification accuracy exceeded 90%.
bol Behörden Online Systemhaus: dog tax registration assistant using Amazon Bedrock AgentCore
Use case typeCustomer service automationUpdated Jun 13, 2026
bol Behörden Online Systemhaus is a German software provider and systems integrator that helps public-sector customers digitize form-management workflows. In collaboration with a city administration, it built FINO to streamline online dog tax registration while meeting German and EU data sovereignty requirements. FINO is an AI assistant that helps citizens submit government forms online. It supports multilingual interactions, retrieves answers from the city knowledge base, guides applicants through required follow-up steps, and helps validate that the submission is complete before it is sent.
- Organization
- bol Behörden Online Systemhaus
- Industry
- Public Sector
- Location
- Germany
- Published
- June 2026
Reported outcomes
5 seconds
timeTime & speed
90%accuracy
Strategic outcomes
Customer experience & trustSimplified online dog tax registrationRisk & complianceSupported data sovereignty complianceCustomer experience & trustProvided multilingual form guidanceCost efficiencyReduced manual review and follow-up work
Why do we believe this?Outcome claims, sources, and evidence checks
Normalized claim
Time: 5 seconds
Average response time was about 5 seconds.
Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks
- Customer
- bol Behörden Online Systemhaus, City administration
- Provider
- AWS
- Maturity
- Production
- Linked source
- AWS Solutions case study
The solution is deployed in the AWS Frankfurt Region and exposed as a modular web component that can be embedded into existing HTML-based municipal services
Customer identity supportedSource describes one deploymentMaturity supported
Primary read
Use case focus
Showing 3 of 4
- 1Citizen service automation
- 2Form processing automation
- 3Document verification
- Simplify citizens’ online submission for dog tax registration while complying with German and EU data sovereignty regulations.
- Reduce manual review, follow-up work, and errors in municipal form processing.
- Support citizens who need help understanding form requirements in different languages.
- Built FINO as an agentic assistant using Amazon Bedrock AgentCore and Amazon Bedrock.
- The assistant translates or matches citizen questions to the city knowledge base and returns relevant answers.
- It provides step-by-step guidance through requirements such as muzzle rules and proof of liability insurance.
- It uses AI image recognition to identify a dog breed from a photo and determine whether it is on the dangerous-breed list.
- The solution is deployed in the AWS Frankfurt Region and exposed as a modular web component that can be embedded into existing HTML-based municipal services.
- The pilot was fine-tuned based on user feedback.
- Breed identification accuracy exceeded 90%.
- Average response time was about 5 seconds.
- The assistant reduced the need for human intervention and follow-ups.
- The approach improved data quality and created a reusable pattern for other municipal applications.
Architecture
FINO is an agentic assistant built on Amazon Bedrock AgentCore and Amazon Bedrock. It runs in the AWS Frankfurt Region, retrieves answers from a city knowledge base, supports multilingual guidance, validates required documents, and uses AI image recognition for dog breed identification before embedding into existing HTML services as a modular web component.
Sources & evidence1
Evidence: Medium65/100Evidence strength
- Customer explicitly identified
- Deployment status explicitly supported
- Primary source available
- Quantified outcome available
- Technical implementation details available
Type: Customer StoryPublished: Jun 8, 2026Publisher: AWSEvidence: VendorConfidence: High
AI-generated summary. Verify important details with the linked sources before relying on this case.
Explore related AI use cases
Customer evidence
Provider evidence
Browse the catalog
Was this useful?
Community
Comments
No published comments yet.