ai_evals
record what a run produced, so it outlives the jobs that produced it
Called by a run's own flow as its last step. The answers and scores a run produced live in its jobs, which have their own retention; this copies them onto the run's rows. Reading a run does the same, so this is what covers a run nobody opened.
post/w/{workspace}/ai_evals/experiments/collect
Path parameters
workspacestring required
Query parameters
idstring uuid required
Response
how many of the run's cases are recorded
integer required