Snowflake has built an internal semantic layer that sits between raw data and downstream consumers (dashboards, AI agents, analytics tools), translating physical database schemas into governed business metrics and dimensions.
This approach resolved the problem of conflicting answers to the same question by providing a single source of truth, and it delivered measurable gains: in July 2025, Snowflake's internal teams executed over 320,000 queries through this unified semantic layer.
The layer also improved AI accuracy dramatically—text-to-SQL accuracy jumped from 20% to over 90% when semantic context was added, making it a foundational pattern for enterprises managing millions of data sources.
What happened
Snowflake built an internal semantic layer—a governed data abstraction that translates raw database tables into consistent business metrics and dimensions accessible to both AI agents and dashboards. In July 2025 alone, over 400 internal users ran more than 5,400 queries through the product data science agent using this semantic layer, while over 5,600 Snowflake employees across all teams ran over 320,000 queries through a broader semantic layer covering sales, HR, support and other functions.
Why it matters
Without a shared semantic context, the same question (e.g., 'What is an active customer?') yields conflicting answers across different tables and metric definitions. The semantic layer solves this by establishing one source of truth for data meaning, enabling AI agents to execute queries faster (avoiding the overhead of finding and understanding raw data sources) and more cost-efficiently (reducing token consumption and repeated computation). In AtScale's benchmark testing, adding semantic context increased text-to-SQL accuracy from 20% to more than 90% across 40 business questions.
What to watch
Snowflake integrated semantic views with dbt (a data build tool) for version control and CI/CD, and paired them with semantic view materializations that intelligently preaggregate metrics across specified dimension combinations to reduce query latency. The semantic views are also interoperable with Apache Ossie, an open standard for semantic models, allowing portability across tools and platforms.
Ask the AI about this article →
Snowflake's internal challenge was not a shortage of data but a surfeit of conflicting context. The company collects petabytes of telemetry across queries, warehouses and user interactions, yet the same business question could yield multiple answers depending on which table and metric definition was consulted. This fragmentation makes it impossible for either humans or AI agents to trust a single version of the truth—a problem that compounds when AI systems are trained at scale on inconsistent definitions.
The semantic layer solves this by introducing a standardized translation layer between physical tables and downstream consumers. Instead of exposing raw data directly to dashboards or agents, a semantic view wraps those tables with governed business logic, dimensions (like region), and metrics (like compute spend). This consolidation delivers three concrete benefits: AI agents execute faster because they bypass the discovery and sampling phase; they consume fewer tokens because the semantic layer pre-materializes relationships and preaggregated data; and text-to-SQL accuracy soars because the model receives precise business context rather than raw column names.
Snowflake's own adoption metrics validate the pattern. Over 5,600 employees across multiple teams ran more than 320,000 queries in a single month (July 2025) through the unified layer, and the accuracy uplift from semantic context—jumping from 20% to over 90% in benchmark tests—demonstrates that this abstraction is not a convenience but a necessity for enterprises relying on AI agents to interpret data at scale.
AI-summarized, only the topics you pick — one digest a day via Email, Slack, or Discord.
Free · takes 30 seconds · unsubscribe anytime
Ask AI anything about this article. Q&As are published on this page for other readers too.
Anthropic is privately hoping to file for its initial public offering by the end of this month, targeting a ra…
Broadcom is reportedly seeking to borrow up to $100 billion in debt financing to support growth efforts at Ant…
As AI technology matures, the bottleneck in the industry is moving beyond semiconductor constraints like GPUs…
Elice Group, a South Korean AI infrastructure provider, announced the launch of the country's first AI data ce…
On August 12, AT&T's Chief Data and AI Officer said OpenAI models power about 25% of the telecom's total AI us…
On August 11, IBM announced a multi-year $240 million agreement with Together AI to deploy NVIDIA HGX B300 sys…
