Artificial intelligence news.
Straight from the original announcements.

Greenlight’s Luna resolves over 90% of security cases autonomously

November 6, 2026, 17:55By the AI News Bites Editorial TeamSource: AWS
Greenlight’s Luna resolves over 90% of security cases autonomously
Image: AWS

Greenlight Financial says its Luna system resolves more than 90 percent of up to 4,000 security and risk cases each month without human intervention. Built on Amazon Bedrock AgentCore, the system uses a tiered network of more than 30 specialized agents to triage alerts and investigate complex cases.

Key points
  • Luna resolves more than 90 percent of up to 4,000 monthly cases without human intervention.
  • The system uses more than 30 specialized agents across security and risk domains.
  • Tier 2 investigates the 10 percent of cases that require deeper reasoning.
  • AgentCore memory supports a 30-day episodic window and longer-term resolution knowledge.
  • Greenlight expanded Luna from SOC operations into financial risk assessment within two months.

A multi-agent system for high-volume alerts

Greenlight provides financial products for families, including debit cards, savings tools, and connected devices such as the Family Hub and Pet Tracker. According to AWS, its security operations center receives 3,000, 4,000 security and risk alerts per month from sources including dark web breach-card reports, identity and access anomalies, infrastructure monitoring, and financial risk systems.

Before Luna, a single dark web breach-card notification could require an analyst to check whether the card was active, remove duplicate notifications, review customer session data, and examine open support tickets. AWS says this process took 15-30 minutes per case.

Greenlight built Luna as a hierarchical multi-agent system on Amazon Bedrock AgentCore. A Tier 1 supervisor performs initial triage using more than 30 specialized agents covering areas such as identity, endpoint detection, observability, asset inventory, payment processing, customer support, threat intelligence, and remediation automation. The median triage time for routine cases is single-digit seconds, according to AWS.

Tier 2 investigation and persistent memory

Cases that fall below Tier 1’s confidence threshold are escalated to a Tier 2 supervisor. AWS says this layer handles the 10 percent of cases requiring multi-step reasoning, including deeper correlation across three to five data sources and the creation of investigation reports with evidence chains for human review.

Luna is available through automated ingestion from Tines SOAR, direct API access for Security, Risk, and ProdOps engineers, and a Claude Desktop extension for on-call engineers. The system can also process urgent escalations on demand or batch cases through Amazon EventBridge and Amazon Simple Notification Service.

Amazon Bedrock AgentCore memory gives Luna both a 30-day rolling episodic memory and longer-term memory for semantic preferences and resolution templates. AWS describes a case in which Luna learned that a recurring Tuesday maintenance access pattern was expected and began allowing it automatically instead of flagging it each week.

A separate learning pipeline captures case resolutions with AWS Lambda, stores and deduplicates patterns in DynamoDB, and feeds actionable learnings back to the supervisors. AWS says this increased Luna’s autonomous resolution rate from 83 percent with Tier 1 alone to more than 90 percent with Tier 1, Tier 2, and the learning system combined.

Expansion from security operations to financial risk

Greenlight expanded Luna into financial risk assessment within two months of its SOC deployment, according to AWS. The company added specialized agents and a risk-domain supervisor while keeping the existing infrastructure largely unchanged.

For dark web breach-card alerts, Luna receives reports from Mastercard and internal feeds, checks Galileo to verify the card and review its status and transaction history, then consults DynamoDB to identify repeat notifications or previously remediated cards. AWS presents the expansion as an example of how an agent architecture built for security operations can also support financial risk triage in a regulated environment.

For users and security teams, the approach is designed to handle routine alerts at machine speed while sending more complex cases to people with additional context. Greenlight also avoids building and operating the agent runtime and memory capabilities itself by using Amazon Bedrock AgentCore, according to AWS.

Related news

AWS details four ways to speed up Amazon Bedrock AgentCore sessions
For developersNovember 13, 2026, 23:02

AWS details four ways to speed up Amazon Bedrock AgentCore sessions

AWS has outlined four architecture patterns for reducing session startup delays in Amazon Bedrock AgentCore runtime, including snapshot-based initialization, build hooks…

For developers
For developersNovember 13, 2026, 17:14

Open Agentic Web Challenge offers $13,000 for interoperable AI agents

A global group of technology, research, standards and civil society organizations has launched the Open Agentic Web Challenge, offering $13,000 for open and…

AWS upgrades AgentCore runtime with faster starts and stronger isolation
Products and toolsNovember 12, 2026, 18:59

AWS upgrades AgentCore runtime with faster starts and stronger isolation

AWS has announced updates to the Amazon Bedrock AgentCore runtime, giving AI agent sessions faster startup, more compute capacity and expanded isolation for data. The…