Analytics agents need the context your team keeps in their heads.
Cassis brings it together: a living context layer between your data and your business. Sharpened by every conversation, governed by your data team, fueling all your agents.
Your context stays yours. Use the web app or work headless with Git and MCP.
The context was always scattered and stale. Analytics agents turn that into production risk.
Every table, dashboard, and metric hides human decisions. Without that context, agents guess.
Business evolves, the data stack changes, new domains open. Without maintenance, agents drift.
Hey @data-team the board deck says 4,215 active customers but the revenue dashboard says 3,892. Which one do I use? Exec meeting in 2h
Board deck pulls from Looker, anyone with a login in the last 90 days. Revenue dash uses Metabase, filters on paid_plan = true Both are "active customers."
Based on the customers table, you currently have 5,104 active customers.
Great, now we have four numbers. Which one goes on the slide.
Approved context, wherever your agents work.
Before SQL gets written, Cassis turns the question into a trusted data path: the concepts involved, the definitions your team approved, the joins that are valid, and the rules that shape the answer.
Your context lives in a Git repository you own, with changes reviewed through pull requests. Use it in Cassis or through MCP in the agents you already use.
Try for free
“With Cassis, our analytics agent goes straight to the exact context it needs. It no longer has to explore Snowflake and reconstruct the database before every question, so adding Cassis not only makes it safer, but also faster.”
Cassis builds your context and keeps it current.
Cassis bootstraps from your data stack and documentation. Questions, corrections, and source changes help enrich it over time. Your team reviews updates in the web app or through pull requests in Git.
based on active status
Governance without becoming the bottleneck.
-
The queue handles itself.
Related issues are grouped, traced to the definition or model behind them, and ranked by potential impact.
-
Drift surfaces before it breaks.
Schema changes, rule changes, and rename collisions arrive as flagged updates, not Slack alerts from finance.
-
Every ontology object has receipts.
Owner, source, Git history, last review. Roll back any change. Trace any answer to the context that produced it.
Numbers you can defend in the meeting.
Every answer shows its work.
Ambiguity surfaces. It does not hide.
Cross-domain questions get the joins right.
Augments your trusted data stack.
Cassis fits into your existing data engineering workflows, from reviewing changes in Git to serving context to your agents through MCP.
Notes on data, meaning, and context
Your data context should be debuggable
How a tree of business domains makes analytics context easier to debug, maintain, and retrieve without overloading the agent.
How to assemble context for analytics agents from your existing assets
Your schema, dbt, query logs and docs already hold much of the context an analytics agent needs. Here's how to recover it without inventing what isn't there.
What breaks when you point an analytics agent at your dbt project
GitLab, Mattermost, Cal-ITP: 13 public dbt projects and 5,284 models. Here is the context their metadata still cannot establish for an analytics agent.
Discuss your analytics agentproject with us
Book a call with our founding team, compare your setup with what the most advanced data teams are doing, and see how Cassis can help you build trusted agents grounded in governed, maintained context.