How HPE Zerto built an agentic troubleshooting system with Amazon Bedrock
HPE Zerto built an agentic troubleshooting system powered by Amazon Bedrock that runs on-premises inside the customer environment. This post describes the multi-agent architecture, the on-premises deployment model built with Strands Agents, and the engineering challenges of grounding agents in live disaster recovery data.
HPE Zerto, a company specializing in hybrid and multi-cloud infrastructure resilience, has developed an agentic troubleshooting system utilizing Amazon Bedrock's AI capabilities. This system aims to assist with configuration issues, system health monitoring, and rapid issue resolution. Deployed within Zerto's on-premises environment, the system offers a natural language interface for users to engage with AI-powered assistance.
The architecture comprises a UI layer for user interaction, an agentic layer housing AI agents, and an intelligence layer handling data processing. Amazon Bedrock, chosen for its secure enterprise deployment and model flexibility, powers the system. Content security is ensured using Amazon Bedrock Guardrails, while per-tenant quotas and limits are managed through AWS CloudWatch, DynamoDB, and Lambda. Observability is provided via CloudWatch telemetry data.
The agentic system streamlines data protection and disaster recovery, offering sub-agents to handle various tasks such as investigating health issues, performing setup tasks, and accelerating feature adoption. This integration with Zerto's existing UI enables efficient troubleshooting without adding operational burden, particularly beneficial during critical events like ransomware attacks or service disruptions.
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.
