Greenlight builds autonomous SOC solution on AgentCore
Understand this story
Greenlight Financial built an autonomous security operations center (SOC) solution called Luna on Amazon Bedrock AgentCore. According to the AWS Machine Learning Blog, of up to 4,000 security and risk events per month, more than 90% are resolved without human intervention. However, in regulated environments, Luna is designed only to triage and make recommendations, and does not autonomously execute remediation without explicit policy approval; remediation is authorized and executed by human analysts or approved automation policies. The solution also covers autonomous triage of financial and business risk cases, which is still in progress and launched about a month ago; the script execution flow combines the AWS DevOps Agent interface and skills framework, with a 90-second execution limit.
AI overview based on source reports · Updated 15 min ago
Coverage timeline
Follow the coverage to explore different perspectives.
- AWS Machine Learning BlogHow Greenlight Financial built an autonomous SOC solution on Amazon Bedrock AgentCore
Greenlight Financial's Luna, built on Amazon Bedrock AgentCore runtime and memory, autonomously resolves more than 90 percent of its 3,000–4,000 monthly security and risk cases, using a tiered supervisor architecture with over 30 specialized agents and episodic memory for continuous learning. The system triages dark web breach-card alerts, identity anomalies, and financial-risk events in seconds, escalating complex cases to a Tier 2 supervisor and human analysts. Greenlight later extended Luna into financial risk triage within two months by adding new specialized agents and a risk-domain supervisor to the existing infrastructure.
Activity for this story
Not enough continuous observations to show a trend yet.