Greenlight Financial says Luna autonomously resolves more than 90% of up to 4,000 monthly cases
AWS profiled Greenlight Financial’s Luna, a security operations system built on Amazon Bedrock AgentCore. Greenlight says it handles up to 4,000 security and risk cases a month and resolves more than 90% without human intervention, while requiring explicit authorization for remediation.

Full Report
In an article published November 6, 2026, AWS profiled Greenlight Financial’s Luna, an autonomous security operations center solution built on Amazon Bedrock AgentCore. Greenlight receives 3,000–4,000 monthly alerts involving dark web breach cards, identity and access anomalies, infrastructure, and financial risk. The company says Luna handles up to 4,000 cases per month and resolves more than 90% without human intervention.
Luna uses a tiered supervisor design: Tier 1 handles high-volume triage, while Tier 2 investigates more complex cases. The Tier 1 supervisor orchestrates more than 30 specialized agents. AWS reports a median triage time of seconds for routine cases, compared with 15–30 minutes for manual handling. Luna’s episodic memory retains recent events and outcomes in a rolling 30-day window. A case-learnings pipeline, AWS says, helped lift autonomous resolution from 83% with Tier 1 alone to more than 90% with Tier 1, Tier 2, and learnings combined.
Greenlight says it expanded Luna from SOC operations into financial risk assessment within two months of deployment, and estimates it avoids 900–1,800 hours of routine manual work monthly. The system is accessible through Tines SOAR ingestion, direct API access, and a Claude Desktop extension. Its stated role is to triage and recommend—not independently authorize remediation: action requires explicit policy approval and human or approved automated authorization. Broader autonomous triage for financial and business risk cases remains in progress.
Why This Matters
The deployment provides a concrete example of security-case triage extending into financial risk assessment, while drawing a clear line between automated recommendations and authorized remediation. Greenlight’s reported case volume, triage times, and resolution rate give readers specific measures to assess the scale and claimed performance of the system.
Evidence
Start with the primary evidence, then review supporting sources and context.
Primary Evidence
1How Greenlight Financial built an autonomous SOC solution on Amazon Bedrock AgentCore
Adam Maksimuk
“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.”
Recommended signals
Recommended by brand, topic, and recent related coverage