Can you build a dependable knowledge graph out of LLM calls that never answer the same way twice?Netflix makes every LLM...

Can you build a dependable knowledge graph out of LLM calls that never answer the same way twice?Netflix makes every LLM output fit an ontology before it becomes a fact, so its root-cause agents start with what engineers used to piece together by hand. Fixing mistakes is harder: a mislabeled thread spreads into the facts built on it, and removing it means tracking what each fact came from.https://benjaminhan.net/posts/20261030-netflix-observability-knowledge-graph/?utm_source=mastodon&utm_medium=social#AI #KnowledgeGraphs #AgenticSystems #NeurosymbolicAI #SoftwareEngineering