Skip to navigation

Label Agent Conversation

View as Markdown

Mark one conversation Flagged or Looks Fine with an optional reason; labeling it again replaces the label. The response then shows what the Grader itself said.

Authentication

AuthorizationBearer

Bearer authentication of the form Bearer <token>, where token is your auth token.

Path parameters

grader_idstringRequired
project_idstringRequired
agent_idstringRequired

Request

This endpoint expects an object.
conversationKeystringRequired1-256 characters
verdictenumRequired
Allowed values:
reasonstring or nullOptional<=2000 characters

Response

Successful Response
conversationKeystring
graderVerdictenum or null
The Grader's own verdict, shown once the owner has answered.
Allowed values:
labelobject
labelsobject

Errors

401
Unauthorized Error
403
Forbidden Error
404
Not Found Error
409
Conflict Error
422
Unprocessable Entity Error
503
Service Unavailable Error