What problem does the semantic layer solve?

Without a semantic layer, the same question like "What is an active customer?" yields different answers across different tables because each table may use different metric definitions. The semantic layer creates one authoritative source of truth for business logic, ensuring consistent answers whether the query comes from a dashboard, AI agent, or ad hoc user.

How much did AI query accuracy improve with semantic context?

In AtScale's benchmark testing, adding semantic context increased text-to-SQL accuracy from 20% to more than 90% across 40 business questions on TPC-DS.

How many queries ran through Snowflake's semantic layer in July 2025?

Over 400 distinct internal users ran more than 5,400 queries through the product data science agent and semantic layer in July 2025 alone, and over 5,600 internal employees across all Snowflake teams ran over 320,000 queries using the broader semantic layer in sales, HR, support, and other areas.

Large Language ModelsAI Business & IndustrySnowflake AI BlogAug 18, 2026Aug 18, 2026, 16:01 JST

Snowflake builds internal semantic layer to unify AI agent data queries

Send on LINE

3 Key Points

What happened
Snowflake built an internal semantic layer—a standardized data interface that sits between raw data tables and downstream consumers (dashboards, AI agents, and analytics tools)—to ensure consistent business logic across the company. In July 2025 alone, over 400 internal users ran more than 5,400 queries through the product data science agent, and over 5,600 employees across all Snowflake teams ran over 320,000 queries using the broader semantic layer in sales, HR, support, and other areas.
Why it matters
Without shared context, the same question (e.g., "What is an active customer?") yields conflicting answers across different tables and metric definitions. A semantic layer eliminates this by providing one trusted source of truth. AI agents using semantic views see faster execution and lower token costs, and 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 is using native dbt integration for version control and CI/CD on semantic views, semantic view materializations to optimize performance, and Cortex Agents with custom routing instructions to automatically find the right context for queries. The company also uses Cortex Sense to help route questions to relevant datasets across the long tail of data.

Not sure about something? Ask the AI

Questions and answers are published on this page.

Summaries like this, in your inbox every morning.

Get news like this every morning, free

Context & Analysis

Snowflake's investment in a semantic layer addresses a persistent problem in data organizations: the gap between raw data and actionable insight. When petabytes of data exist across millions of sources without standardized definitions, even straightforward business questions generate conflicting answers. The problem compounds with AI agents, which operate at machine speed and scale—if a Cortex Agent reports one number while a legacy dashboard shows another, there is no clear source of truth. By curating an internal semantic layer, Snowflake created a single, governed interface that translates physical database schemas into business logic that every consumer (human and machine) can trust.

The performance and cost benefits reinforce this architectural choice. Semantic views materialize preaggregated data, allowing AI agents to skip the time-consuming steps of finding, understanding, and sampling multiple raw data sources. Agents also become more token-efficient when they can reference curated dimension and metric relationships instead of reasoning through raw table joins. The July 2025 usage numbers—over 320,000 queries across the company—show that once the semantic layer is in place and accessible, adoption spreads quickly across multiple teams and use cases, from product analytics to HR and support.

FAQ

What problem does the semantic layer solve?: Without a semantic layer, the same question like "What is an active customer?" yields different answers across different tables because each table may use different metric definitions. The semantic layer creates one authoritative source of truth for business logic, ensuring consistent answers whether the query comes from a dashboard, AI agent, or ad hoc user.
How much did AI query accuracy improve with semantic context?: In AtScale's benchmark testing, adding semantic context increased text-to-SQL accuracy from 20% to more than 90% across 40 business questions on TPC-DS.
How many queries ran through Snowflake's semantic layer in July 2025?: Over 400 distinct internal users ran more than 5,400 queries through the product data science agent and semantic layer in July 2025 alone, and over 5,600 internal employees across all Snowflake teams ran over 320,000 queries using the broader semantic layer in sales, HR, support, and other areas.

Snowflake AI BlogRead Original Article

Send on LINE

AI news that matters for your work, delivered every morning.

Pick your industry and the AI tools you use, and get news related to your work every day.

Get it free

Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.