CEcekura
test_framework

Generate scenario instructions with AI

Changed on

Write caller instructions and an expected outcome for a new evaluator of the agent, guided by extra_instructions, and return them. Nothing is saved. Usually takes under a minute.

post/test_framework/v3/scenarios/generate-instructions/

Request

  • Base URL
    https://api.cekura.ai
  • URL
    https://api.cekura.ai/test_framework/v3/scenarios/generate-instructions/
  • Auth
    • API key in header X-CEKURA-API-KEY
    • or HTTP bearer
    • or HTTP bearer

Request body

agent_idinteger required

Agent the evaluator will test.

extra_instructionsstring required

What the evaluator should test, in plain language.

Response

status'completed' | 'failed'

failed when the job could not produce its result; see error / errors.

agent_idinteger
instructionsstring nullable
expected_outcome_promptstring nullable
errorstring nullable

Why the job failed, when it did.

Changes