Flavia Saldanha, a consulting knowledge engineer, joins host Kanchan Shringi to debate the evolution of knowledge engineering from ETL (extract, remodel, load) and knowledge lakes to fashionable lakehouse architectures enriched with vector databases and embeddings. Flavia explains the business’s shift from treating knowledge as a service to treating it as a product, emphasizing possession, belief, and enterprise context as essential for AI-readiness. She describes how unified pipelines now serve each enterprise intelligence and AI use instances, combining structured and unstructured knowledge whereas guaranteeing semantic enrichment and a single supply of reality. She outlines key elements of a contemporary knowledge stack, together with knowledge marketplaces, observability instruments, knowledge high quality checks, orchestration, and embedded governance with lineage monitoring. The episode highlights methods for abstracting tooling, future-proofing architectures, implementing knowledge privateness, and controlling AI-serving layers to forestall hallucinations. Saldanha concludes that knowledge engineers should transfer past pure ETL pondering, embrace product and NLP abilities, and work intently with MLOps, utilizing AI as a co-pilot fairly than a substitute.
Dropped at you by IEEE Pc Society and IEEE Software program journal.
Associated Episodes
