NEWS · COMPANIES · #1788
Netflix presents ontology‑driven E2E knowledge graph for observability
Netflix engineers Prasanna Vijayanathan and Renzo Sanchez‑Silva presented at QCon London an approach to observability that unifies MELT telemetry into a queryable end‑to‑end knowledge graph. They described replacing reactive monitoring with an AI‑driven operational ontology and agentic workflows (using Claude and graph databases) to enable automated triage, root‑cause analysis and self‑healing at Netflix scale (reported ~38M events/sec, 65M concurrent streams peak).
KEY POINTS
- Netflix engineers Prasanna Vijayanathan and Renzo Sanchez‑Silva presented at QCon London an approach to observability that unifies MELT telemetry into a queryable end‑to‑end knowledge graph.
- They described replacing reactive monitoring with an AI‑driven operational ontology and agentic workflows (using Claude and graph databases) to enable automated triage, root‑cause analysis and self‑healing at Netflix scale (reported ~38M events/sec, 65M concurrent streams peak).
- Demonstrates a real‑world application of AI/knowledge‑graph techniques to automate observability and AIOps at internet scale, potentially changing how large services handle incident detection and remediation.
WHY IT MATTERS
Demonstrates a real‑world application of AI/knowledge‑graph techniques to automate observability and AIOps at internet scale, potentially changing how large services handle incident detection and remediation.