An alert e-mail that explains itself in a few words, and a dry run that says whether a rule would fire on the current data and why — the verdict always decided by code, never by the model. Two AI additions to alert rules. The AI paragraph adds a short explanation, written from the alert's own data, to the message a firing rule sends. Check with AI tries the rule on the current data, sends nothing, and explains the verdict. In both, code decides whether the rule fires; the model is told that verdict as a fact and only words it.
This site needs JavaScript for the full experience. Every page above is reachable without it.