Cassis is where it lives: a living context layer between your data and your business. Sharpened by every conversation, governed by your data team, fueling all your agents.
Thanks. We'll be in touch.
Something went wrong. Please try again.
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.
@data-team board deck says 4,215 active customers, revenue dash says 3,892. Exec meeting in 2h. Which one?
Board deck includes trials, 90-day login. Revenue dash uses paid_plan = true, excludes trials. Both labeled active customers.
Based on the customers table, you currently have 5,104 active customers.
So that is three numbers. Which one for the slide?
Updating the definitions doc. Again.
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.
How many active customers grew revenue last quarter?
customer_revenue_qoq_growth fact_revenue_monthly, dim_customer status = active AND subscription_tier = paid 2,335 customers
+$1.4M ARR growth, 60% of active base
Cassis bootstraps from your data stack and documentation. From there, every question, correction, schema change, and ambiguity enriches the ontology.
Built from your stack.
56 entities · 142 metrics · 14 dimensions
Continuously enriched.
"How many loyal customers churned?"
3 definitions detected for loyal_customer across Sales, CS, and Marketing threads.
Agent could not answer discount_tier
Asked 4 times this week. No definition found in the ontology.
invoices.discount_amount → net_discount
Detected from dbt manifest diff. 14 downstream definitions reference it.
Related issues are grouped, traced to the definition or model behind them, and ranked by potential impact.
Schema changes, rule changes, and rename collisions arrive as flagged updates, not Slack alerts from finance.
Owner, source, edit history, last review. Roll back any change. Trace any answer to the context that produced it.
Proposed from 9 questions. Source: UTM fields and campaigns table.
Two attributed definitions. Sales: 3+ renewals. CS: >12mo subscription.
Column renamed to net_discount. Downstream definitions flagged before refresh.
$2.45M
Two definitions exist. Which one do you mean?
AI agents don't just need a semantic layer. They make it impossible for humans to operate without one.
AI tools are enabling business users to contribute directly to dbt models and metric definitions. The data stack isn't ready.
AI agents don't remove the human cost of making data useful. They redistribute it.
Cassis is in early access. We're working with data teams at companies with well-structured data stacks (between 200 and 1000 people) who are ready to move beyond duct-taped context.
Thanks. We'll be in touch.
Something went wrong. Please try again.
