Unified NPL Document Classifier
Centralises the ingestion and classification of 25 document categories across entire NPL portfolios.
The business process
Centralised case-file management across portfolio waves, replacing per-project classifiers with one unified model.
What the agent reads
- Massive document flows from NPL portfolios
What it produces
- Documents classified into 25 categories
- Structured extraction per category feeding portfolio valuation
How it works
Mass ingestion feeds a unified classifier; extraction models per category then structure the data used to value the portfolio.
Runs on
- Domain-tuned SLM/LLM/VLM serving
- Governable agent orchestration
Related agents
Agents that share the same industry or the same capabilities.
ClassifyExtractSearch & answer
Secured NPL Data Acquisition Agent
Reads 130 million pages of loan and property files and extracts 330 datapoints per case for due diligence.
130Mpages processed
ClassifyExtract
Unsecured NPL Classification Agent
Classifies 3.7 million documents and pinpoints statute-of-limitation dates for unsecured portfolios.
3.7Mdocuments processed
ClassifyExtractReconcile
NPL Payment Proposal Due Diligence Agent
Verifies every repayment plan against the customer database before it is sent to the debtor.
290,000pages a year, 197 datapoints