Investigations · natural language

Investigation copilot

Questions in plain language are answered only from documents the user is allowed to see (role- and attribute-based access is applied at retrieval time). Every sentence carries a citation; a grounding check removes any sentence that no source supports before the answer is shown.

Synthetic data only. No real customers, officials, companies, transactions or institutions. A PiR2-IT product, demonstrator by Marius Mihail Russo-Got.

Agentic AML Hyperautomation — live demo — overview

More in this demo

• Access control
• Insider threat
• Compliance matrix
• Data sovereignty
• Connectors & APIs
• Training (LMS)
• Executive view
• Onboarding & screening
• Monitoring & rules
• Alert queue
• L2 cases
• SAR / STR
• KYC · UBO resolver
• Conflicts of interest
• Organised networks
• Trace X → Y
• Public procurement
• AI governance
• Client RFI & FIU exchange
• Security & resilience
• Architecture
• Audit log
• Policy & thresholds
• 38-module map