A record of where a piece of data came from and every system and transformation it passed through on the way to a report or model.
Data Lineage underpins AI compliance and auditability. If an LLM hallucinates or produces a biased response, engineers need to trace the exact training data or RAG context document behind it. Complete lineage records let teams debug Agentic Workflows and demonstrate regulatory compliance.
See also Agentic Workflows, Data Mobilization, Data Lakehouse and Vector Database.