Session

Building SCAR: Low-Cost, High-Throughput Supply Chain Ingestion and Agentic RAG

When global supply chains fracture, decision-makers cannot wait for manual analysis. Developed alongside Israel’s National Emergency Authority, SCAR is an operational radar providing real-time monitoring and early warnings across critical national supply chains.

This lightning talk breaks down SCAR’s Dual-Engine Operational Framework, built entirely on AWS serverless architecture. We will explore how we pair a deterministic KPI pipeline—utilizing Amazon Athena and S3 for low-cost, high-throughput global trade data ingestion with an Agentic RAG chatbot powered by Amazon Bedrock. Specifically, we focus on the design of our Intelligent Agent Router, which autonomously splits queries across structured SQL tables and unstructured intelligence feeds.

Attendees will walk away with a production-ready pattern for routing hybrid data streams to deliver localized, actionable strategic guidance under crisis conditions.

Ravit Cohen-Segev

Horizon Scanning Lab - Data Scientist

Haifa, Israel

Actions

Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.

Jump to top