Skip to main content

Create an autopilot evaluation

POST 
/targets/:tid/evaluations/autopilot

The system generates the evaluation spec (tasks/personas/principles) from the grounded corpus, sized server-side by depth (no entity counts in the body). One dimension per call — run once per dimension to cover several. Returns the new evaluation + a pollable job.

Request​

Responses​

Successful Response

Response Headers
    Idempotent-Replayed

    Present and true when this response is a replay.