Cassis documentation
Analytics agents need business context beyond raw data; the hard part is keeping it current and governed. Cassis is the living context layer between your data and those agents. It uses approved context to generate and run the SQL behind every answer, then turns questions, corrections, and source changes into proposed updates for your data team to review.
Use Cassis through the web app or fully headless. People and agents ask through the web app, Slack, or any MCP client; data teams maintain context through the web app, Git, MCP, or CLI; warehouse integrations supply the current data behind answers.
Understand Cassis See where it fits Follow a question from any client through Cassis to your warehouse and back as an answer. Start here Try the guided demo Find a context gap, teach Cassis once, and see the next answer improve. Ask from an MCP client Connect any MCP-compatible client. Claude Code, Claude Desktop, and Cursor are examples. Request access for your warehouse Connect Cassis to your own data and business definitions.