Presentation: Ontology‐Driven Observability: Building the E2E Knowledge Graph at Netflix Scale
Netflix processes 38M events/sec. They replaced reactive monitoring with agentic workflows and knowledge graphs — here's how they automated root-cause analysis at scale.
Why it matters
Netflix's production observability system demonstrates a concrete deployment of Claude-driven agents and graph databases for autonomous triaging and self-healing in a high-volume telemetry environment. Practitioners managing similar scale can extract operational patterns for agent grounding, knowledge representation, and autonomous remediation workflows.
The key facts
6 to knowNetflix observability handles 38M events/sec
Replaced reactive monitoring with AI-driven operational ontology
Agentic workflows using Claude and graph databases
Unified MELT telemetry (Metrics, Events, Logs, Traces) into queryable knowledge graphs
Enabled automated triaging, root-cause analysis, and self-healing systems
Published as presentation at InfoQ (Oct 9, 2026)
Go to the source
InfoQ AI/MLinfoq.com
Publisher excerpt: Prasanna Vijayanathan and Renzo Sanchez-Silva share how Netflix tackles observability across 38M events/sec. They discuss replacing reactive monitoring with an AI-driven operational ontology and agentic workflows using Claude and graph databases. They explain how unifying MELT telemetry into…