Teams building on OriginChainDB. Named only with permission.
We publish a customer's name, workload and numbers only after they have signed off on the exact wording. No customer is named on this page today. The three cards below are the workload shapes we see most often.
Three shapes we see every week.
Retrieval for production assistants
Documents, their embeddings and the full-text postings that catch exact terms live in one store. One write, one commit, one query path — no sync job between a vector index and the system of record.
RAG on one engine →Fraud and risk graphs
Entities as rows, relationships as graph edges, behaviour as vectors — traversed and scored in the same request, inside the customer's region, with a per-request audit log.
Fraud detection →Personalisation at request time
Catalogue rows, taste vectors and click history queried together under a latency budget, on a dedicated instance that scales compute and storage independently.
Personalisation →Bring your workload. We'll measure it with you.
A structured pilot on a dedicated instance, with success criteria agreed up front and a written report at the end.