Skip to main content
Commission 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.
Calls POST /v1/autoimprove/job

​
Options

​
string
required
The production agent to improve. It is never modified until you promote.
​
string
required
The metric that defines success: a pass/fail metric, or a threshold variant of a scale metric (for example “PII Handling >= 4”). Roark measures the pass rate of this metric across simulated calls.
​
string
required
Human-readable label for the objective, shown everywhere the job appears.
​
number
The pass-rate percentage that counts as fixed. Defaults to 90.
​
string
An existing agent to stage changes on instead of the default shadow clone. Must be a different agent from agentId, on the same provider.
​
string
The provider integration whose credentials Roark uses. Omit to use the project’s active integration for the agent’s provider. The integration must have agent config writes enabled.
​
string
An existing simulation run plan to validate with. Omit to let Roark author its own suite.
​
integer
Cap on decision turns. Defaults to 50.
​
integer
Cap on simulated calls dialed. Defaults to 200.

​
Example

Every command also takes the global options and sets one of the exit codes.