Gurpinder Dhillon

Every insurance data product, underwriting or claims, hinges on one question: is this the same person or organization across systems? Verisk answers it once, at scale, treating the answer as a data product.

Most AI failures in production do not look like bugs. The model runs, the output is confident, and the logic checks out, but the system acted on the wrong version of reality. This session walks through a real world, anonymized enterprise fraud and risk case study where an AI system kept making technically correct decisions about the wrong entity, because the identity data underneath it was fragmented across systems. The root cause was not model quality. It was the absence of a consistent, real-time answers to a basic question: who, or what, is this actually referring to. Now that agents are moving from assistive to autonomous, this becomes an action problem, not a reporting one. An agent that resolves entities incorrectly does not just produce a wrong answer on a dashboard, it flags the wrong account, approves the wrong claim, or blocks the wrong customer. This session covers what changed when an identity resolution layer was introduced, and a practical way to audit whether your own agentic AI systems are sitting on the same fragmented foundation.

Most Agentic AI failures aren't model failures — they're identity failures. When agents act on fragmented, mismatched customer data, confident decisions become expensive mistakes. Drawing on a global banking case study, this session gives data leaders a concrete framework for embedding Identity Intelligence into Agentic AI workflows — and measuring it as a first-class ROI and risk metric.

75% of GenAI projects fail to scale—not because the models lack sophistication, but because they’re built on fragmented data. If your systems don’t know who they're talking about, how can your AI deliver reliable insights? This talk unveils how real-time Entity Resolution (ER) is becoming the silent engine behind trusted, AI-ready data architecture. We will discuss how organizations across financial services, public safety, and digital platforms are embedding ER into modern data stacks—delivering identity clarity, regulatory confidence, and faster outcomes without the drag of legacy MDM. You’ll learn: Why ER is foundational for AI trust, governance, and analytics Patterns for embedding ER into streaming and event-driven architectures How ecosystem partners and data platforms are amplifying ER value How to build trust at the entity level—without slowing down innovation Whether you’re modernizing architecture, launching AI programs, or tightening compliance, this session will equip you to embed trust from the ground up.