EvaluationRunObject

One rehearsal of every saved conversation an agent has.

Field	Type	Description
`agent_id`	string (uuid)
`created_at`	string (date-time)
`error`	string	Why nothing was rehearsed, when nothing was.
`failed`	integer
`finished_at`	string (date-time) or null
`id`	string (uuid)
`not_checked`	integer
`object`	`evaluation_run`
`passed`	integer
`results`	array of EvaluationResult	Every saved conversation's outcome, once the run is finished.
`started_at`	string (date-time) or null
`status`	string	`queued`, `running` or `finished`. Ask again until it is `finished`. New words may be added.