Technical evaluation demonstrates automated metadata extraction and text-to-SQL querying across heterogeneous databases, highlighting lightweight governance without heavy enterprise platforms.
The exponential growth of heterogeneous enterprise data spread across CSV files, JSON documents, SQLite databases, and PostgreSQL instances has made it increasingly difficult for organizations to know what data they own, where it resides, and whether it can be trusted. DataVista AI is an AI-powered data catalog and intelligence copilot that automatically crawls structured data sources to construct a searchable metadata catalog. The system extracts schemas, computes statistical health profiles, discovers table-level relationships, generates business glossaries, and exposes an interactive AI copilot capable of conversational Text-to-SQL generation. A dual-engine language model manager routes requests to a cloud primary model with automatic failover to a secondary provider, while an Enterprise Privacy Mode and PII scrubbing layer ensure that raw sensitive values never leave the trust boundary. Built on a FastAPI backend, a ten-page Streamlit frontend, a lightweight Model Context Protocol (MCP) tool registry, and a LangChain-driven agent loop, DataVista AI demonstrates that automated, explainable data governance can be delivered without a heavyweight enterprise catalog platform.
No takes yet. Share an insight, caveat, or question.
P et al. (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: