Platform / Data & Context
Approved data becomes governed AI context.
All retrieval flows through the Data API — with row-level policies, classification ceilings, knowledge base ACLs, and lineage back to source.
No direct vector store access
Agents must not call Qdrant or object storage directly. The Data API enforces tenant scope, row_filter access policies, and classification ceilings at retrieval time.
Knowledge bases bind documents, chunk policy, and retrieval ACLs. Data products expose curated gold tables with owners and classification for governed agent workflows.
Shipped capabilities
- Central Data API for all agent retrieval
- Row-level access policies (row_filter) per dataset
- Knowledge bases with classification and ACL
- Qdrant vector store with tenant isolation
- Open lakehouse (Iceberg/MinIO) for governed datasets
- OpenLineage integration for data lineage
- Connector catalog for enterprise systems