How Greenlight Financial built an autonomous SOC solution on Amazon Bedrock AgentCore
Greenlight Financial resolves more than 90% of up to 4,000 monthly security and risk cases without human intervention using Luna, a tiered multi-agent system on Amazon Bedrock AgentCore. This post covers the architecture, episodic memory for continuous learning, and the expansion from SOC operations into financial risk triage.
Greenlight Financial processes over 90% of their 3,000-4,000 monthly security and risk alerts without human intervention, using an autonomous security operations center (SOC) powered by Amazon Bedrock AgentCore. Central to this solution is Luna, an advanced agent system that employs a tiered supervisor architecture to handle routine cases and escalate complex ones to human analysts.
The system comprises more than 30 specialized agents, each tackling specific alert types like dark web breach-card alerts, identity anomalies, and financial-risk events. By leveraging Amazon Bedrock AgentCore's runtime and memory capabilities, Luna can triage cases in seconds, learn from resolution patterns, and operate within stringent financial regulations.
Written by urgent.news from AWS Machine Learning's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
This story
This is one outlet's version. Read the fullest account.
- Getting started with Web Answer on Amazon Bedrock AgentCore aws.amazon.com
