NPL Portfolio Onboarding Agent
Populates data tapes and core systems from heterogeneous NPL files the moment a new portfolio arrives.
The business process
Credit acquisition and onboarding of new NPL portfolios, drastically reducing manual data entry in the early phases of case management.
What the agent reads
- Heterogeneous legal, banking and real-estate NPL files
- Mortgage registration notes, loan contracts, guarantees, ODA, mortgage extracts
What it produces
- Extraction organised into objects: property, subject, guarantee, auction, ownership
- Granular cadastral data, certified identities, loan details and the chronology of encumbrances
How it works
Document classification and hierarchical object extraction with models trained on complex documents such as mortgage registrations, loan contracts, guarantees and sale orders.
Runs on
- Domain-tuned SLM/LLM/VLM serving
- Ontology-driven workflows
- APIs & MCP connectors
Related agents
Agents that share the same industry or the same capabilities.
Secured NPL Data Acquisition Agent
Reads 130 million pages of loan and property files and extracts 330 datapoints per case for due diligence.
Unsecured NPL Classification Agent
Classifies 3.7 million documents and pinpoints statute-of-limitation dates for unsecured portfolios.
NPL Payment Proposal Due Diligence Agent
Verifies every repayment plan against the customer database before it is sent to the debtor.