Create a new assistant test

POST 
/ai/assistants/tests

Creates a comprehensive test configuration for evaluating AI assistant performance

application/json

Body

required

name Name (string)required

Possible values: non-empty and <= 255 characters

A descriptive name for the assistant test. This will be used to identify the test in the UI and reports.

description Description (string)

Possible values: <= 1000 characters

Optional detailed description of what this test evaluates and its purpose. Helps team members understand the test's objectives.

telnyx_conversation_channel TelnyxConversationChannel (string)

Possible values: [phone_call, web_call, sms_chat, web_chat]

destination Destination (string)required

Possible values: non-empty

The target destination for the test conversation. Format depends on the channel: phone number for SMS/voice, webhook URL for web chat, etc.

max_duration_seconds Max Duration Seconds (integer)

Possible values: >= 1 and <= 3600

Maximum duration in seconds that the test conversation should run before timing out. If not specified, uses system default timeout.

test_suite Test Suite (string)

Possible values: <= 100 characters

Optional test suite name to group related tests together. Useful for organizing tests by feature, team, or release cycle.

instructions Instructions (string)required

Possible values: non-empty and <= 5000 characters

Detailed instructions that define the test scenario and what the assistant should accomplish. This guides the test execution and evaluation.

rubric

object[]

required

Possible values: >= 1

Evaluation criteria used to assess the assistant's performance. Each rubric item contains a name and specific criteria for evaluation.

Array [

name stringrequired

Label for the evaluation criterion, e.g., Empathy, Accuracy, Clarity.

criteria stringrequired

Specific guidance on how to assess the assistant’s performance for this rubric item.

]

201: Returns the created test configuration with assigned test ID

application/json

• Schema
• Example (from schema)

Schema

test_id uuidrequired

Unique identifier for the assistant test.

name Name (string)required

Human-readable name of the test.

description Description (string)

Detailed description of the test's purpose and scope.

telnyx_conversation_channel TelnyxConversationChannel (string)required

Possible values: [phone_call, web_call, sms_chat, web_chat]

destination Destination (string)

Target destination for test conversations.

max_duration_seconds Max Duration Seconds (integer)

Maximum allowed duration for test execution in seconds.

test_suite Test Suite (string)

Test suite grouping for organizational purposes.

instructions Instructions (string)

Detailed test scenario instructions and objectives.

rubric

object[]

required

Evaluation criteria used to assess test performance.

Array [

name stringrequired

Label for the evaluation criterion, e.g., Empathy, Accuracy, Clarity.

criteria stringrequired

Specific guidance on how to assess the assistant’s performance for this rubric item.

]

Evaluation criteria used to assess test performance.

created_at date-timerequired

Timestamp when the test was created.

{
  "test_id": "123e4567-e89b-12d3-a456-426614174000",
  "name": "Customer Support Bot Test",
  "description": "string",
  "telnyx_conversation_channel": "phone_call",
  "destination": "string",
  "max_duration_seconds": 0,
  "test_suite": "string",
  "instructions": "string",
  "rubric": [
    [
      {
        "criteria": "Responds within 30 seconds",
        "name": "Response Time"
      }
    ]
  ],
  "created_at": [
    "2024-01-15T09:00:00Z"
  ]
}

422: Validation Error

application/json

• Schema
• Example (from schema)

Schema

detail

object[]

Array [

loc

object[]

required

Array [

anyOf

• MOD1
• MOD2

string

integer

]

msg Message (string)required

type Error Type (string)required

]

{
  "detail": [
    {
      "loc": [
        "string",
        0
      ],
      "msg": "string",
      "type": "string"
    }
  ]
}

Request samples

• cURL

---

curl -L 'https://api.telnyx.com/v2/ai/assistants/tests' \
-H 'Content-Type: application/json' \
-H 'Accept: application/json' \
-H 'Authorization: Bearer <TOKEN>' \
-d '{
  "name": [
    "Customer Support Bot Test",
    "Sales Assistant Evaluation"
  ],
  "description": "string",
  "telnyx_conversation_channel": "phone_call",
  "destination": [
    "+15551234567",
    "assistant-id"
  ],
  "max_duration_seconds": 0,
  "test_suite": "string",
  "instructions": [
    "Act as a frustrated customer who received a damaged product. Ask for a refund and escalate if not satisfied with the initial response."
  ],
  "rubric": [
    [
      {
        "criteria": "Assistant responds within 30 seconds",
        "name": "Response Time"
      },
      {
        "criteria": "Provides correct product information",
        "name": "Accuracy"
      }
    ]
  ]
}'

Response samples

• 201
• 422

---

{
  "test_id": "123e4567-e89b-12d3-a456-426614174000",
  "name": "Customer Support Bot Test",
  "description": "string",
  "telnyx_conversation_channel": "phone_call",
  "destination": "string",
  "max_duration_seconds": 0,
  "test_suite": "string",
  "instructions": "string",
  "rubric": [
    [
      {
        "criteria": "Responds within 30 seconds",
        "name": "Response Time"
      }
    ]
  ],
  "created_at": [
    "2024-01-15T09:00:00Z"
  ]
}

{
  "detail": [
    {
      "loc": [
        "string",
        0
      ],
      "msg": "string",
      "type": "string"
    }
  ]
}