AI-based Process Automation
In the public sector, millions of existing corporate records are matched against newly submitted reports containing incomplete or inconsistent information. For a public sector client, we implemented an agent-based AI solution that independently analyzes and researches such information and maps it to existing database entries. This fully AI-driven process automation saves the customer time and is highly scalable. We collaborate with market-leading energy providers and offer our customers efficient and future-proof solutions for their highly complex energy-system-specific processes.
Key Areas of Cooperation
Until now, the assignment process had been carried out manually using the dual-control principle. The process was time-consuming and hardly scalable. The project’s goal was to automate the initial assignment in order to reduce turnaround times and costs without sacrificing the existing review as a quality control measure. The main challenge lay in reliably assigning companies based on incomplete and inconsistent data. Company names were spelled differently, and additional information—such as location or registry details—was not always available or was maintained inconsistently. As a result, rule-based processes quickly reached their limits.
Key factors:
- Handling Fuzzy and Inconsistent Input Data
- High Transparency of Decisions
- Maintaining Human Control Despite AI-Based Process Automation
- Agent-Based AI
- Large Language Models (Open Source)
- Observability and LLMOps
Our Project KPIs
…in the correct assignment of companies
Results & Outlook
Agent-based AI achieves an accuracy rate of approximately 95 % in correctly assigning companies, which is on par with the accuracy of manual assignments to date. At the same time, turnaround time and operational effort are significantly reduced, as complex research and decision-making processes are automated and AI-supported. In addition, business units can track assignments in real time, evaluate them retrospectively, and further improve the solution based on data.
The transparent agent architecture lays the foundation for further automation steps. In the future, the solution can be expanded to include additional data sources and used for further classification and search processes in the public sector.
Our Services and Case Studies in Artificial Intelligence
- AI Consulting and Workshops,
- Implementations,
- AI-powered data classification,
- AI Document Management,
- AI-based process automation,
- AI agents,
- Machine Learning,
- LLMs
Artificial Intelligence Consulting
Sustainable know-how transfer for your company thanks to our AI consulting: workshops, use case evaluation, implementation consulting …
AI Document Management
LLM-Based Document Analysis and Processing in Healthcare …
AI-powered Data Classification
Automated Classification of Structured Datasets in the Public Sector …
We'd be happy to advise you
Dr. Danny Hucke
We understand that every project is unique. Dr. Danny Hucke looks forward to speaking with you to find customized solutions.
