Launch HN: Relvy (YC F24) – On-call runbooks, automated
Not a pilot. Relvy's AI agent automates on-call runbooks across observability stacks—resolving production issues in minutes instead of hours.
Why it matters
A YC-backed AI agent purpose-built for enterprise DevOps. Rather than generic LLM reasoning (Claude Opus scores 36% on root cause analysis), Relvy ships specialized telemetry tools + runbook anchoring to eliminate hallucinations and cut investigation time. Early adoption signal in a high-stakes, high-value workflow.
The key facts
7 to knowRelvy AI launched by Bharath and Simranjit (YC F24)
Claude Opus 4.6 scores 36% accuracy on OpenRCA dataset for autonomous root cause analysis
Specialized tools for telemetry: anomaly detection, log pattern search, span tree reasoning
Deployment options: local Docker, Helm, cloud SaaS
Integrates with Slack alerts and AWS CLI for automated mitigation
Runbook-anchored agent design reduces agentic exploration and cognitive load on engineers
Product developed over ~1 year working with early customers
Go to the source
Hacker Newsrelvy.ai
Publisher excerpt: Hey HN! We are Bharath, and Simranjit from Relvy AI (https://www.relvy.ai). Relvy automates on-call runbooks for software engineering teams. It is an AI agent equipped with tools that can analyze telemetry data and code at scale, helping teams debug and resolve production issues in minutes. Here’s…