Skip to main content
POST
Clarify what evaluator scenarios should cover

Authorizations

Authorization
string
header
required

OAuth access token issued by Cekura for connected apps.

Body

Clarify what a batch of evaluator scenarios should cover before generating them.

Improving existing evaluators is not done here — the Cekura agent reads the evaluators attached to its turn and writes changes back with the ordinary scenario write endpoints. See test_framework.scenario_chat_context.

user_message
string
default:""

What the generated evaluators should cover (e.g., 'cover refund disputes and angry callers'). Do not use for agent prompt/config improvements.

agent_id
integer | null

Agent the generated evaluators are for. Required on the first turn; on a follow-up it may be omitted and is read off session_id.

project_id
integer | null

Project ID - optional, automatically inferred from evaluators if not provided

session_id
integer | null

Session ID for tracking - automatically created if not provided

num_scenarios
integer
default:1

Number of scenarios the clarification should be sized for

Required range: x >= 1
knowledge_base
integer[]

Knowledge Base file IDs for additional context

tool_ids
string[]

Tools that will be enabled on the generated evaluators (validated up front)

inbound_phone_numbers
integer[]

Inbound numbers that will be attached to the generated evaluators (validated up front)

Response

progress_id
string
required

Use this to poll for results at /scenario-agent-progress/?progress_id={id}

session_id
integer
required

Session tracking ID