Questions? We have answers.

Kanlet is the semantic context layer for intelligent systems. It sits between your business systems and your AI stack. It unifies context from across the business - warehouses, BI tools, business systems, data platforms, unstructured content and tribal knowledge in people’s heads - into a single graph that agents and analysts query in real time. Without one, every new agent deployment starts with months of manual context building. With one, every new agent inherits the organization's full institutional memory on day one.

Kanlet connects to 15+ systems: Snowflake, Databricks, BigQuery, Redshift, dbt, Airflow, Tableau, Looker, Power BI, and Postgres, among others. Once connected, lineage, query history, BI semantics, tags, and quality signals flow in automatically through scheduled and event-based workflows - no manual mapping required. More database and application connectors are in the pipeline.

Kanlet extracts structural metadata (databases, schemas, tables, views, columns with types and nullability), relationship-level lineage (upstream and downstream asset dependencies), operational data (last-modified timestamps, creation history), and quality signals where your quality tools are connected (Monte Carlo, Anomalo, Bigeye, and others).

You configure a sync schedule per connector - from on-demand to daily or weekly batch. Kanlet handles incremental updates automatically, so your context always reflects the current state of your stack without any manual effort. Changes in source systems - new tables, schema changes, deleted assets - are picked up on the next scheduled crawl.

No. Kanlet only reads metadata - schema names, table structures, column definitions, lineage relationships, ownership, and timestamps. Your actual data never leaves your systems. Kanlet never queries the rows in your tables, never stores data payloads, and never moves data between systems. What gets extracted is only the metadata about your data, not the data itself.

Kanlet layers on top of your existing data stack. You can run Kanlet alongside Microsoft Purview or Snowflake Horizon or Databricks Unity Catalog - pulling metadata from all into a unified context layer rather than rebuilding from scratch. Built on open APIs and Iceberg-native formats, context stored in Kanlet stays portable: it is not locked to any vendor's proprietary schema. Switch AI frameworks, add new systems, or consolidate tools - the context layer moves with you.