AI Engineer World's Fair 2026 — unofficial import demo

An LLM doesn't copy facts into your knowledge graph. It synthesizes them: entities merge across sources, and later data invalidates earlier facts. By the time your agent retrieves "patient has a penicillin allergy," the origin — an EHR record, a lab report, or something typed into a chatbot — is gone. This talk covers engineering lineage into a lossy, generative pipeline: episode-to-fact links as structural graph properties, provenance that survives entity resolution, metadata projection (tag a source once; it follows every derived node and edge), and the query semantics of filtering facts by ancestry, including mixed-trust parentage. Deletion is the inverse problem: GDPR erasure propagates back through the same derivation edges. Compliance gets an audit trail; engineers get agents they can debug instead of black boxes.