Start an Autoimprove job
Changed onCommission Roark on an objective. It clones the agent into a staging shadow (or uses your designated staging agent), authors a validation suite of simulated callers, measures a baseline, changes the staging configuration, and re-tests until the objective metric passes its target. Production is never touched by the loop; verified changes wait for promotion.
Requires an active provider integration (Vapi, Retell, or ElevenLabs) with agent config writes enabled. One live job per agent: starting a second returns a conflict.
The job runs asynchronously; poll GET /v1/autoimprove/job/{jobId} or watch it in the dashboard. When its status is NEEDS_INPUT, answer via the answer endpoint; when AWAITING_PROMOTE, promote or dismiss.
Request
- Base URLhttps://api.roark.ai
- URLhttps://api.roark.ai/v1/autoimprove/job
- AuthHTTP bearer
Request body
Example request
{
"agentId": "b3b0c8e2-4c1d-4f6a-9e2b-1a2b3c4d5e6f",
"objectiveMetricDefinitionId": "f2f0c8e2-4c1d-4f6a-9e2b-1a2b3c4d5e6f",
"objectiveLabel": "Consent collection should pass",
"targetValue": 90
}Response
The job was created and its loop started.
Changes
- breaking
the response property
/became nullable for the status - warning
added the new
CHANNELenum value to the/response property for the response status
- breaking
- info
endpoint added
- info