Skip to main content
POST
/
test_framework
/
v1
/
scenarios
/
generate-bg
cURL
curl --request POST \
  --url https://api.cekura.ai/test_framework/v1/scenarios/generate-bg/ \
  --header 'Content-Type: application/json' \
  --header 'X-CEKURA-API-KEY: <api-key>' \
  --data '
{
  "num_scenarios": 50,
  "agent_id": 123,
  "assistant_id": "<string>",
  "personalities": [
    123
  ],
  "test_profile": 123,
  "scenario_type": "workflow",
  "attack_type": "",
  "expected_outcome": "<string>",
  "knowledge_base": [
    123
  ],
  "extra_instructions": "<string>",
  "inbound_phone_number": 123,
  "first_message": "Hello",
  "generate_expected_outcomes": false,
  "tags": [
    "<string>"
  ],
  "tool_ids": [
    "TOOL_DTMF",
    "TOOL_END_CALL",
    "TOOL_END_CALL_ONLY_ON_TRANSFER"
  ],
  "folder_path": "<string>"
}
'
{
  "progress_id": "<string>"
}

Authorizations

​
X-CEKURA-API-KEY
string
header
required

API Key Authentication. It should be included in the header of each request.

Body

​
num_scenarios
integer
required

Number of evaluators to generate (1-100)

Required range: 1 <= x <= 100
​
agent_id
integer

ID of the agent to generate evaluator for

​
assistant_id
string

Alternative to agent_id - the assistant ID to generate evaluators for

​
personalities
integer[]

List of personality IDs to use for generated evaluators

​
test_profile
integer

ID of the test profile to assign to generated evaluators

​
scenario_type
enum<string>
default:workflow

Type of scenarios to generate: workflow (standard scenarios), red_teaming_voice (red teaming with voice-suitable prompts only), red_teaming_text (red teaming with all prompts), or knowledge_base (knowledge base scenarios)

  • workflow - workflow
  • red_teaming_voice - red_teaming_voice
  • red_teaming_text - red_teaming_text
  • knowledge_base - knowledge_base
Available options:
workflow,
red_teaming_voice,
red_teaming_text,
knowledge_base
​
attack_type
enum<string> | null

Attack category for red teaming scenarios. Required when scenario_type is red_teaming_voice or red_teaming_text. Categories: system_prompt_leak (attempts to extract the system prompt), data_leak (attempts to extract sensitive data), harmful_content (attempts to generate harmful output), biased_output (attempts to generate biased responses), unauthorized_actions (attempts to trigger unauthorized tool calls or actions), off_task (attempts to derail the conversation away from the agent's purpose)

  • `` -
  • system_prompt_leak - system_prompt_leak
  • data_leak - data_leak
  • harmful_content - harmful_content
  • biased_output - biased_output
  • unauthorized_actions - unauthorized_actions
  • off_task - off_task
Available options:
,
system_prompt_leak,
data_leak,
harmful_content,
biased_output,
unauthorized_actions,
off_task,
null
​
expected_outcome
string | null

Custom expected outcome for the scenario. If not provided, a default is generated based on the attack type.

​
knowledge_base
integer[]

List of Knowledge Base file IDs for the agent to reference during scenario generation

​
extra_instructions
string

Additional instructions to guide evaluator generation

​
inbound_phone_number
integer | null

Phone number ID to use for inbound evaluator

​
first_message
string
default:Hello

Initial message to start the conversation

Maximum string length: 1000
​
generate_expected_outcomes
boolean
default:false

If true, expected outcomes will be generated for each evaluator

​
tags
string[]

List of tags to apply to all generated scenarios

​
tool_ids
string[]

List of tool IDs to use for generated evaluators

Example:
[
  "TOOL_DTMF",
  "TOOL_END_CALL",
  "TOOL_END_CALL_ONLY_ON_TRANSFER"
]
​
folder_path
string | null

Folder path to assign generated scenarios to (e.g., 'folder_name' or 'parent.child')

Response

​
progress_id
string