Semantic Modeling FAQ

Frequently asked questions about semantic modeling in Precog.

Compatibility & Requirements

Which destinations support semantic views?

Currently, Snowflake is the only destination that supports semantic views. Semantic views power Snowflake Cortex Analyst, enabling natural language queries against your data warehouse.

We expect to add support for additional destinations as more platforms adopt semantic layer capabilities.

Can I generate a semantic view for multiple sources at once?

Yes. When your connection includes multiple data sources, Precog generates a unified semantic view that spans all of them. This means you can ask questions that join across sources — for example, correlating CRM data with accounting data in a single natural language query.

How do I get access to semantic modeling?

Semantic modeling is available through Precog AI Assistants. Contact Precog support to enable the AI Assistants feature for your workspace. Once enabled, you can create an AI Assistant from the AI Assistants section in the left-hand workspace navigation.

Generation & Timing

How long does it take to generate a semantic view?

Semantic view generation typically takes a few minutes, though it can take longer for very large datasets with many tables and columns.

When is the semantic view generated?

The semantic view is generated automatically when you create an AI Assistant. The foundation model is built once per environment, and the Snowflake semantic view is created from it.

What happens if my source schema changes?

When schema changes are detected (new tables or columns), Precog regenerates the semantic view to reflect the current source structure. The updated view replaces the previous version in Snowflake.

Viewing & Editing

Where can I find my semantic view in Snowflake?

Navigate to your Snowflake database and look for the semantic view in the schema associated with your connection.

Where can I track generation status?

You can check generation status from the AI Assistants page in the workspace navigation.

Why can't I see my generated semantic view?

If you don't see your semantic view after successful generation, check these common causes:

  1. Generation still in progress — After the AI Assistant is created, it can take a few minutes for the semantic view to appear in Snowflake. Wait and check again.

  2. Destination isn't Snowflake — Semantic views only work with Snowflake destinations. Verify that your connection uses a Snowflake warehouse as the destination.

  3. Default warehouse mismatch — Your Snowflake user's default warehouse must match the warehouse where your data was shipped. If they don't match, Snowflake may not show the semantic view.

Quality & Optimization

How can I improve my semantic view quality?

The most impactful thing you can do is write a clear, detailed use case description when setting up your AI Assistant. Vague descriptions like "financial reporting" produce generic views. Specific descriptions produce views tuned to your actual needs.

A good use case includes:

  • Specific metrics you want to track (e.g., "invoice aging, payment trends, cash flow")
  • Key entities in your data (e.g., "customers, suppliers, invoices")
  • How you want to slice the data (e.g., "by department and month")

For detailed guidance with examples and templates, see Writing Effective Use Case Descriptions.

For ongoing optimization after your semantic view is generated, see Knowledge Base and Semantic Layer.

Need More Help?

For additional questions about semantic modeling, contact Precog support through the in-app chat or visit our support resources.