Glossary
Agent Run
An agent run is one full pass through the pipeline for one question, with an id, time, cost, and result. Observability sits on runs, not on a vague sense of the system.
Also called اجرای عامل
Each run should be replayable, or at least explainable. Without a run id, a policy reject and a model error cannot be traced.
Let’s make your processes agentic
Where do we start?