Notes for humans. Mostly

JUN 24, 2026

The state of agentic analytics, from 50 real data teams

Field notes from 50+ conversations with data teams: the five stages of agentic analytics, what breaks at each, and what teams want next.
JUN 11, 2026

The hard part of self-maintaining context for analytics agents

Context is now table stakes for analytics agents. The new problem is keeping it true as the business keeps moving.
JUN 3, 2026

The semantic layer is for humans, not machines

AI agents don't just need a semantic layer. They make it impossible for humans to operate without one.
MAY 19, 2026

Your data stack is about to get a lot more contributors

AI tools are enabling business users to contribute directly to dbt models and metric definitions. The data stack isn't ready.
MAY 14, 2026

There's still no free lunch in data analytics

AI agents don't remove the human cost of making data useful. They redistribute it.

Start trusting youranalytics agents

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.

Notes for humans. Mostly.

The state of agentic analytics, from 50 real data teams

The hard part of self-maintaining context for analytics agents

The semantic layer is for humans, not machines

Your data stack is about to get a lot more contributors

There's still no free lunch in data analytics

Start trusting youranalytics agents