Skip to main content
POST
Train Policy Adapter
Start asynchronous training for an activated policy import. Training Studio re-reads the import’s original document, generates and judges examples, and trains a policy-specific LoRA adapter. Call this after Import Policy and Activate Rules. Import extracts candidate rules; training is only accepted once those rules are activated (409 if the import is still pending review). Then poll Get Training Status until training succeeds or fails.
Training uses the original imported document, not only the extracted rule definitions. If that document has expired under your retention policy, re-import and activate the policy before training.

Path Parameters

string
required
The activated policy import to train.

Request Body

The body is optional. Omit it to use Training Studio defaults.
number
Optional maximum generation spend in US dollars for this run.
integer
Optional number of generated training examples per extracted rule.

Response

Returns 202 Accepted after the training run has been created.
string
Policy import being trained.
string
Training Studio run identifier.
string
Initial status reported for the training run.
string
Human-readable next step, when present.
object
Endpoint used to monitor this run.

Error Responses

Example

cURL