---
title: "Create a new assistant test"
method: POST
path: "/ai/assistants/tests"
tags: ["Assistants"]
---

# Create a new assistant test

`POST /ai/assistants/tests`

Creates a comprehensive test configuration for evaluating AI assistant performance

## Request body

- CreateAssistantTestRequest — Request model for creating a new assistant test. This model defines all the required and optional parameters needed to create a comprehensive test for an AI assistant, including test configuration, evaluation criteria, and scheduling options.
  - `name` string, required — A descriptive name for the assistant test. This will be used to identify the test in the UI and reports.
  - `description` string — Optional detailed description of what this test evaluates and its purpose. Helps team members understand the test's objectives.
  - `telnyx_conversation_channel` 'phone_call' | 'web_call' | 'sms_chat' | 'web_chat'
  - `destination` string, required — 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` integer — Maximum duration in seconds that the test conversation should run before timing out. If not specified, uses system default timeout.
  - `test_suite` string — Optional test suite name to group related tests together. Useful for organizing tests by feature, team, or release cycle.
  - `instructions` string, required — Detailed instructions that define the test scenario and what the assistant should accomplish. This guides the test execution and evaluation.
  - `rubric` object[], required — Evaluation criteria used to assess the assistant's performance. Each rubric item contains a name and specific criteria for evaluation.
    - `name` string, required — Label for the evaluation criterion, e.g., Empathy, Accuracy, Clarity.
    - `criteria` string, required — Specific guidance on how to assess the assistant’s performance for this rubric item.

## Response `201`

Returns the created test configuration with assigned test ID

- AssistantTestResponse — Response model containing complete assistant test information. Returns all test configuration details including evaluation criteria, scheduling, and metadata. Used when retrieving individual tests or after creating/updating tests.
  - `test_id` string, uuid, required — Unique identifier for the assistant test.
  - `name` string, required — Human-readable name of the test.
  - `description` string — Detailed description of the test's purpose and scope.
  - `telnyx_conversation_channel` 'phone_call' | 'web_call' | 'sms_chat' | 'web_chat', required
  - `destination` string — Target destination for test conversations.
  - `max_duration_seconds` integer — Maximum allowed duration for test execution in seconds.
  - `test_suite` string — Test suite grouping for organizational purposes.
  - `instructions` string — Detailed test scenario instructions and objectives.
  - `rubric` object[], required — Evaluation criteria used to assess test performance.
    - `name` string, required — Label for the evaluation criterion, e.g., Empathy, Accuracy, Clarity.
    - `criteria` string, required — Specific guidance on how to assess the assistant’s performance for this rubric item.
  - `created_at` string, date-time, required — Timestamp when the test was created.

## Other responses

- `422` — Validation Error

---

[API](https://skmtc.net/team-telnyx/apis/telnyx-api-2.md) · [All operations](https://skmtc.net/team-telnyx/apis/telnyx-api-2/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/team-telnyx/telnyx-api-2/revisions/8f5f4e537994/schema)