List Evaluators

cURL

curl --request GET \
  --url https://api.cekura.ai/test_framework/v1/scenarios/ \
  --header 'X-CEKURA-API-KEY: <api-key>'

{
  "count": 123,
  "next": "https://api.cekura.ai/example/v1/example-external/?page=4",
  "previous": "https://api.cekura.ai/example/v1/example-external/?page=3",
  "results": [
    {
      "id": 123,
      "name": "<string>",
      "personality": 123,
      "personality_name": "<string>",
      "phone_number": "<string>",
      "expected_outcome_prompt": "<string>",
      "instructions": "<string>",
      "scenario_language": "af",
      "scenario_type": "instruction",
      "tags": "<unknown>",
      "agent": 123,
      "inbound_phone_number": 123,
      "inbound_phone_number_data": "<string>",
      "metrics": [
        123
      ],
      "metric_names": "<string>",
      "first_message": "Hello",
      "tool_ids": "<unknown>",
      "test_profile": 123,
      "test_profile_data": {
        "id": 123,
        "agent": 123,
        "name": "<string>",
        "information": {}
      },
      "created_at": "2023-11-07T05:31:56Z",
      "updated_at": "2023-11-07T05:31:56Z",
      "last_updated_by": 123
    }
  ]
}

GET

test_framework

scenarios

cURL

curl --request GET \
  --url https://api.cekura.ai/test_framework/v1/scenarios/ \
  --header 'X-CEKURA-API-KEY: <api-key>'

{
  "count": 123,
  "next": "https://api.cekura.ai/example/v1/example-external/?page=4",
  "previous": "https://api.cekura.ai/example/v1/example-external/?page=3",
  "results": [
    {
      "id": 123,
      "name": "<string>",
      "personality": 123,
      "personality_name": "<string>",
      "phone_number": "<string>",
      "expected_outcome_prompt": "<string>",
      "instructions": "<string>",
      "scenario_language": "af",
      "scenario_type": "instruction",
      "tags": "<unknown>",
      "agent": 123,
      "inbound_phone_number": 123,
      "inbound_phone_number_data": "<string>",
      "metrics": [
        123
      ],
      "metric_names": "<string>",
      "first_message": "Hello",
      "tool_ids": "<unknown>",
      "test_profile": 123,
      "test_profile_data": {
        "id": 123,
        "agent": 123,
        "name": "<string>",
        "information": {}
      },
      "created_at": "2023-11-07T05:31:56Z",
      "updated_at": "2023-11-07T05:31:56Z",
      "last_updated_by": 123
    }
  ]
}

Authorizations

X-CEKURA-API-KEY

string

header

required

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

Query Parameters

page

integer

A page number within the paginated result set.

page_size

integer

Number of results to return per page.

agent_id

integer

Filter evaluators by agent ID Example: 2142

project_id

integer

Filter evaluators by project ID Example: 1

assistant_id

string

Filter evaluators by assistant ID Example: asst_1234567890

Minimum string length: 1

Response

200 - application/json

count

integer

Example:

123

string<uri> | null

Example:

"https://api.cekura.ai/example/v1/example-external/?page=4"

string<uri> | null

Example:

"https://api.cekura.ai/example/v1/example-external/?page=3"

results

object[]

Show child attributes

results.id

integer

Unique identifier for the AI agent Example: 123

results.name

string

Name of the scenario

Maximum string length: 80

results.personality

integer | null

Foreign key reference to the personality used in this scenario

results.personality_name

string

Name of the personality used in this scenario Example: "Normal Male"

results.phone_number

string

results.expected_outcome_prompt

string

Expected outcome prompt for the scenario Example: "The user should be able to complete the order"

results.instructions

string

Detailed instructions that guide the AI agent's behavior in this scenario

results.scenario_language

enum<string> | null

Language code for the scenario (ISO language code)

af - Afrikaans
ar - Arabic
bg - Bulgarian
zh - Chinese Simplified
cs - Czech
da - Danish
nl - Dutch
en - English
fi - Finnish
fr - French
de - German
el - Greek
hi - Hindi
he - Hebrew
hu - Hungarian
id - Indonesian
it - Italian
ja - Japanese
ko - Korean
ms - Malay
multi - Multilingual
no - Norwegian
pl - Polish
pt - Portuguese
ro - Romanian
ru - Russian
sk - Slovak
es - Spanish
sv - Swedish
th - Thai
tr - Turkish
ta - Tamil
uk - Ukrainian
vi - Vietnamese

Available options:

af,

ar,

bg,

zh,

cs,

da,

nl,

en,

fi,

fr,

de,

el,

hi,

he,

hu,

id,

it,

ja,

ko,

ms,

multi,

no,

pl,

pt,

ro,

ru,

sk,

es,

sv,

th,

tr,

ta,

uk,

vi,

results.scenario_type

enum<string>

default:instruction

Type of scenario (instruction, real_world_smart, or real_world_fixed)

instruction - Instruction
real_world_smart - Real World Smart
real_world_fixed - Real World Fixed

Available options:

instruction,

real_world_smart,

real_world_fixed

results.tags

any

List of tags associated with this scenario for categorization Example: ["tag1", "tag2", "tag3"]

results.agent

integer

Foreign key reference to the AI agent that owns this scenario

results.inbound_phone_number

integer | null

Foreign key reference to the phone number used for inbound calls

results.inbound_phone_number_data

string

Details of the phone number used for inbound calls

results.metrics

integer[]

List of metrics associated with this scenario for evaluation

results.metric_names

string

List of metric names associated with this scenario Example: ["Metric 1", "Metric 2", "Metric 3"]

results.first_message

string

default:Hello

The initial message that the AI agent will send when the scenario starts

Maximum string length: 1000

results.tool_ids

any

List of tool IDs that are available for use in this scenario Example: ["TOOL_DTML", "TOOL_END_CALL"]

results.test_profile

integer | null

Test profile ID Example: 123

results.test_profile_data

object

Details of the test profile associated with this scenario Example:

{
    "id": "<integer>",
    "agent": "<integer>",
    "name": "<string>",
    "information": {
        "user_name": "John Doe",
        "user_email": "[email protected]",
    }
}

Show child attributes

results.test_profile_data.id

integer

results.test_profile_data.agent

integer

results.test_profile_data.name

string

Maximum string length: 255

results.test_profile_data.information

object

Information fields for the test profile Example:

{
    "user_name": "John Doe",
    "user_email": "[email protected]",
}

Show child attributes

results.test_profile_data.information.{key}

string

results.created_at

string<date-time>

Timestamp when the scenario was created

results.updated_at

string<date-time>

Timestamp when the scenario was last updated

results.last_updated_by

integer

ID of the user who last updated this scenario

Get Evaluator Create Evaluator

⌘I

API Reference

Authorizations

Query Parameters

Response