Notes for humans. Mostly.
Thanks. We'll be in touch.
Something went wrong. Please try again.
Thanks. We'll be in touch.
Something went wrong. Please try again.
Your stack already holds much of the context an analytics agent needs. Here's how to recover what's there without inventing what isn't.
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.
Freshness controls can tell you a definition is old. Real use can reveal that it is wrong. We checked fifteen vendors to see who closes the loop.
Rules, metrics, or worked examples? We measured which context representations shorten an LLM's path to a correct answer, and what the wrong turns taught us about good context.
Analytics agents need context. Great. How should you structure it? Lessons from six months of building, testing, and rebuilding it.
Field notes from 50+ conversations with data teams: the five stages of agentic analytics, what breaks at each, and what teams want next.
Context is now table stakes for analytics agents. The new problem is keeping it true as the business keeps moving.
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.
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.
