Snowflake Builds New Intelligence that Goes Beyond RAG to Query and Aggregate Thousands of Documents at Once

Why It Matters

The platform removes data silos and governance hurdles, allowing businesses to analyze proprietary unstructured data at scale alongside structured data, which can drive faster, more informed decision‑making and a competitive AI advantage.

Summary

Snowflake unveiled Snowflake Intelligence at its BUILD 2025 conference, featuring Agentic Document Analytics that lets users run SQL‑like queries across thousands of unstructured documents. The new capability treats documents as queryable data sources, extracting and indexing content via Cortex AISQL and delivering sub‑second performance through Snowflake’s interactive tables and warehouses. By unifying structured and unstructured data within a single governed platform, it eliminates the need for separate vector databases and RAG pipelines. The move positions Snowflake ahead of rivals such as Databricks and vector‑database vendors by enabling enterprise‑scale document aggregation and analytics.