Veriteus Technology
Veriteus provides a multimodal behavioral AI platform that analyzes voice, content, and video in real time to flag inconsistencies during interviews, calls, and digital forms. The system marks specific passages where answers diverge, suggests follow-up questions, and runs on-premise or in an EU cloud with a zero-PII architecture. It targets insurance claims, hiring, compliance investigations, and public sector use cases.
- Artificial Intelligence
- Data & Analytics
- Regulatory & Compliance Technology
- Insurance Technology
- Software Only
Funding
Founders
Product
Problem
Traditional deception detection methods rely on voice stress analysis alone, which cannot distinguish natural stress or anxiety from actual deception and often requires storing sensitive voice recordings. These approaches produce high false positive rates and lack the transparency needed for audit-ready decision-making in fraud prevention, compliance, and investigative contexts. Research shows people detect lies with only 54% accuracy, barely above chance, even for experienced judges.
Solution
Veriteus offers a multimodal behavioral AI platform that analyzes linguistic patterns, acoustic markers, and video cues to detect manipulation and inconsistency during digital interactions. The system operates in real time, checking what is said against available files and documents, and flags specific passages where answers diverge. Every flag comes with a suggested follow-up question, so a human interviewer can verify whether the concern holds. The platform processes data temporarily without storing personal information, making it compliant with GDPR and EU AI Act requirements while producing audit-ready, explainable reports. Veriteus runs on-premise or in an EU cloud, and every engagement starts with a pilot on the customer's own closed cases.
Target Audience
Primary customers are insurance companies detecting fraudulent claims before payout, corporate compliance teams conducting internal investigations, HR departments performing background verification, legal and forensic professionals gathering evidence, and public sector agencies managing benefits fraud and regulatory compliance.
Features
- Voice analysis module detects acoustic, prosodic, and linguistic cues, developed with Prof. Julia Hirschberg (Columbia University)
- Content verification checks statements against available files and documents in real time
- Video analysis on roadmap to combine voice and visual signals, targeting over 80% accuracy
- Flags specific passages with confidence scores and suggested follow-up questions for human review
- Zero PII architecture—no voice recordings or personal data stored, only temporary processing
- On-premise or EU cloud deployment options for data sovereignty
- Pilot program lets customers test on their own past cases with known outcomes before live use