Rate a draft
INB-06: record the human verdict — good or bad — against the draft. Accepted in any status: judging a draft after approving or discarding it is exactly when the verdict is clearest.
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Path Parameters
Body
INB-06: a thumb, not a scale — good or bad is all the loop needs.
INB-06: the human verdict on a drafted reply.
Two values, not five stars — a triaging human will click a thumb, not deliberate over a scale, and "good or bad" is all a feedback loop needs.
good, bad Response
Successful Response
How sure the model is. Only HIGH is ever acted on without a human.
high, medium, low auto_drafted, on_demand Where one drafted reply stands.
STALE is its own terminal state rather than a flavour of DISCARDED: "the prospect wrote again before anyone answered" and "a human said no" are different facts, and only the second one says anything about draft quality.
pending_approval, sent, discarded, stale INB-16: the model's 0-100 calibration, clamped into the categorical band. Null for drafts that predate the field. Presentation only — every decision reads the categorical confidence.
INB-06: the human verdict on this draft, when one was given.
good, bad