Vancouver-based INETCO has launched a new AI-assisted investigation module designed to help banks and payment providers review fraud alerts faster without removing human oversight.
INETCO BullzAI Investigate uses specialized AI agents to assemble transaction data, analyze behavioural patterns and triage incoming alerts. It then directs analysts toward the highest-risk cases and provides explainable, auditable risk scores for each recommendation.
The technology runs on a proprietary small language model deployed within the customer’s own environment, ensuring sensitive transaction data remains on-premise. Analyst feedback is also used to refine the system through a supervised machine-learning cycle.
“Rather than replacing analysts, INETCO BullzAI Investigate serves as an intelligent partner that works continuously behind the scenes,” said INETCO Chief Technology Officer Ugan Naidoo.
INETCO says early deployments have reduced investigations that previously took between 10 and 30 minutes to approximately 20 seconds. The company reports a 97% to 99% reduction in investigation time, reviews up to 90 times faster and recommendation precision of approximately 95%.
The company says the module is intended to reduce false positives and the burden of manually reviewing large volumes of fragmented transaction data, allowing fraud teams to concentrate on higher-priority threats.
INETCO will demonstrate the technology during a webinar on July 30 examining how financial institutions are using agentic AI to accelerate fraud investigations.
Be the first to comment