01
You write the skill.
No SQL. No code. Describe what to look at, what counts as worth reporting, and what to do about it — the way you'd brief a new analyst. Pick the tables, set the bounds, done.
“If the gap is under 5%, reply with exactly ‘Nothing to report.’ Otherwise: slice by segment and source, then explain the most likely cause.”
02
It runs on your schedule.
An agent is a task on the same canvas as your SQL, dbt and notebooks — so it runs after your pipelines refresh, against data that's already current. Read-only tools, a query budget, a turn limit.
Every step is written to the run log: which skill and version, which tools it was offered, every query it spent, how it finished.
03
It tells you what matters.
The finding lands in Slack, Teams, or your inbox — with the number, the cause, the confidence, and a link to the query behind it. Not an alert that something moved. An explanation of why.
And on the mornings when nothing's wrong, it says so and gets out of your way.