Enables natural language querying of Karenina benchmark verification results stored in SQLite databases, allowing AI assistants to explore and analyze model performance data without writing SQL manually.
Automatically scans SQLite databases and generates typed CRUD tools for each table, allowing natural language database interaction without exposing raw SQL.
Enables natural-language querying of SQLite databases through a governed semantic layer, with citations and typed abstention for PII or uncertified data.
Enables natural language database interaction with SQLite through JMD documents, allowing CRUD operations and schema management via simple text format.