View Full TranscriptWEBVTT 00:00:00.000 -> 00:00:06.000 Narrator: In this demo, we will show you how Denodo and AWS together are powering agentic AI for the insurance industry. 00:00:06.000 -> 00:00:30.000 Narrator: Enterprises are moving fast on agentic AI, but progress often stalls because critical data is spread across multiple clouds, regions, and on-premises systems, and can't be replicated due to regulatory, sovereignty, or cost constraints. Agentic AI needs live, trusted, contextual data, and without a unified data foundation, organizations struggle to scale impact. 00:00:30.000 -> 00:00:46.000 Narrator: Together, Denodo and AWS address these challenges by delivering a comprehensive, open architecture that enables organizations to leverage their entire data estate across multi-cloud, hybrid, and on-premises environments while ensuring compliance and security. 00:00:46.000 -> 00:01:00.000 Narrator: The Denodo Platform acts as the logical data access layer that simplifies this distributed data, making your entire AWS data ecosystem and the rest of your enterprise information instantly available, governed, and truly AI-ready. 00:01:00.000 -> 00:02:05.000 Narrator: Denodo and AWS help organizations across industries build and deploy AI and analytics solutions successfully. In this demo, we'll walk you through our joint solution capabilities using an example from the auto insurance industry. Imagine you're an auto insurance company that has built and deployed AI agents on Amazon Bedrock and Amazon SageMaker to optimize your claims processing. Current claims processing is hindered by system fragmentation, where critical data is trapped in disconnected systems of record. This leads to problems such as decreased revenues due to loss leakage and subrogation blindness, poor customer satisfaction, and high operational costs caused by long delays in processing claims manually. 00:02:05.000 -> 00:02:43.000 Narrator: Instead of manual audits, this solution deploys a multi-agent system that acts as an autonomous adjuster, fueled by a real-time data fabric. Denodo acts as a logical data fabric that creates a unified, real-time view of the policyholder. It joins claims, policy administration, and billing or payments without moving data, ensuring agents always reason over the system of truth. This provides a rich semantic layer for AI agents with lineage security policies to support data governance requirements. AWS, the cognitive brain, uses Amazon Bedrock to provide the reasoning layer. These agents interpret legal policy language, analyze damage photos, and orchestrate cross-functional workflows. 00:02:43.000 -> 00:03:25.000 Narrator: The result: a move from manual adjudication to straight-through processing with human collaborators for complex, high-value cases. Let's walk through a real-world auto claim where the policyholder files a claim that he was fully stopped at a red light when another car tapped his bumper. The claim states his car was stationary. Here is an Amazon Quick automation for agentic claims processing for insurance. Each step in the automation includes an integration with Denodo to provide the data each AI agent requires. Highlighted in step 2 is the Forensic Assessment AI Agent. 00:03:25.000 -> 00:03:41.000 Narrator: The AI agent receives input from the policyholder's claim and reconciles the vehicle telemetry data with the claim. Based on the live real-time data of the vehicle, it is determining the likelihood of a fraudulent claim. Denodo is the access layer for the Forensic Assessment Agent. The Forensic Assessment Agent is using Denodo MCP integration to access policyholder, claims data, and vehicle telemetry sprawled across on-premises and cloud environments. 00:03:41.000 -> 00:04:08.000 Narrator: \[UI displaying Amazon SageMaker AI notebook\] The power of Denodo's unified semantic layer is the same data available to AI agents can be available to other data consumers. Here is an AWS SageMaker AI notebook, consuming the Denodo Claims Triage logical view. 00:04:08.000 -> 00:04:37.000 Narrator: \[UI showing Denodo Design Studio interface\] Denodo's Design Studio is a no-code graphical interface for implementing logical data products. Denodo provides metadata for data sources and can also synchronize business metadata from Amazon SageMaker Catalog to leverage the existing business semantics already defined to implement a consistent semantic layer across distributed sources. 00:04:37.000 -> 00:04:58.000 Narrator: The business definition and descriptions are defined in Amazon SageMaker Catalog as shown here. The Amazon SageMaker Catalog definitions are synchronized with Denodo to ensure a consistent and trusted semantic layer is implemented. 00:04:58.000 -> 00:05:37.000 Narrator: Denodo's Design Studio makes it easy for data engineers to create logical data products. Here is an example of how easy it is to join disparate data sources together in a join transformation. Denodo provides hundreds of out-of-box functions that includes cleansing, enrichment, date/time conversions, arithmetic, and more. 00:05:37.000 -> 00:05:50.000 Narrator: \[UI showing Global Security Policies in Denodo Design Studio\] Denodo enables you to utilize centralized policies, including granular attribute-based access control, dynamic data masking, an end-to-end data lineage to govern all data once, from on-premises systems to cloud data services, ensuring your users and AI agents have access to the right data while maintaining strict regulatory compliance and building enterprise trust. 00:05:50.000 -> 00:06:09.000 Narrator: Shown here is a global security policy implementing a masking rule based on views and columns that are tagged with PII\_insurance. 00:06:09.000 -> 00:06:50.000 Narrator: With Denodo, the AI agent runs real-time analysis on both the live telemetry data and historical claims systems data stored across different clouds and on-premises systems, predicts likely outcomes, and determines potential fraudulent claims that require a human in the loop, claims that have a high probability for subrogation recovery, and claims that can go to straight-through processing. Denodo provides a unified semantic layer that connects data across AWS data services including Amazon SageMaker Lakehouse, Aurora alongside your non-AWS sources. Denodo ensures all consuming applications, from AI agents to BI tools, have the right business context to generate accurate insights and recommend and execute the right actions. 00:06:50.000 -> 00:06:59.000 Narrator: The fraud detection agent identifies high-risk claims that do not match the vehicle's telemetry data and provides a confidence score and risk analysis. 00:06:59.000 -> 00:07:20.000 Narrator: Since the AI agent's recommendations fall under the confidence score thresholds defined, the AI agent routes this to a fraudulent claim human in the loop to review the claim. If the human resolves the claim, it will go through to the settlement agent to reconcile the claim amount with policy limits. It triggers the payment API if all integrity checks pass. 00:07:20.000 -> 00:07:42.000 Narrator: In this case, it fails to reconcile the claim amount and moves to the next recovery agent. The recovery agent analyzes recovery data and assesses data to look for cases with a high probability of recovery. If it meets its threshold, the recovery agent invokes a settlement API action. If it does not, it goes back through a human in the loop for analysis for high-risk recovery claims. 00:07:42.000 -> 00:08:41.000 Narrator: \[UI displaying summary slides\] By building and running their agentic AI solutions on AWS and Denodo, the insurance carrier reduces loss leakage, specifically through automated coverage verification and fraud detection, directly lower the loss ratio, providing a multi-million dollar impact on the bottom line. Enable an increase in claim volume without increasing headcount by transitioning low-complexity claims to straight-through processing. Accelerates subrogation recovery by identifying third-party liability markers in real-time. The system reduces the cycle time to recovery, improving cash flow and capital reserves. The solution enhances member experience as faster adjudication leads to higher net promoter scores, reduces policyholder churn, and increasing lifetime value. Together, Denodo and AWS help organizations turn their distributed data chaos into a trusted, AI-ready foundation for faster insights, accurate and effective agentic workflows, stronger governance while reducing costs. 00:08:41.000 -> 00:08:45.000 Narrator: Thanks! To learn more, visit: denodo.com/aws. Learn more at denodo.com/aws. Build an AI-ready foundation for autonomous [insurance](https://www.denodo.com/en/solutions/by-industry/insurance) operations. Learn how Denodo and AWS combine a logical data fabric with Amazon Bedrock to power intelligent claims agents. Moving from passive AI experimentation to autonomous, agentic insurance operations requires a unified, trusted view of highly fragmented data. This demo showcases how Denodo and AWS seamlessly integrate to break down data silos across isolated policy administration, claims, and billing systems, as well as external third-party data feeds—all without expensive and slow data replication. See a real-world scenario in which Denodo’s architecture delivers real-time, governed business and operational context directly to advanced AI services such as Amazon Bedrock and Amazon SageMaker. By provisioning intelligent agents with complete visibility, insurers can automatically detect potential fraud indicators using live vehicle telemetry, instantly verify complex coverage bounds, and accelerate straight-through processing. Learn how this unified approach helps carriers reduce loss leakage and drive operational efficiency while maintaining strict human-in-the-loop oversight. What you'll learn: - How Denodo and AWS orchestrate a trusted, real-time data layer optimized for enterprise Agentic AI. - Cross-referencing real-time vehicle telemetry with historical claims to identify complex fraud signatures. - Automating core workflows like straight-through claims processing and subrogation recovery. - Designing data architectures that support robust governance and human-in-the-loop validation for LLMs. ### Role AI DeveloperArchitectBusiness UserDeveloper ### Solutions - AI - IT Modernization ### Industry - [Insurance](/en/solutions/by-industry/Insurance) [Any questions? Contact Us](/contact-us)