Telnyx Ai Assistants Javascript

Telnyx AI Assistants - JavaScript

Installation

npm install telnyx

Setup

import Telnyx from 'telnyx';

const client = new Telnyx({
  apiKey: process.env['TELNYX_API_KEY'], // This is the default and can be omitted
});

All examples below assume client is already initialized as shown above.

Error Handling

All API calls can fail with network errors, rate limits (429), validation errors (422), or authentication errors (401). Always handle errors in production code:

try {
  const assistant = await client.ai.assistants.create({
    instructions: 'You are a helpful assistant.',
    model: 'openai/gpt-4o',
    name: 'my-resource',
  });
} catch (err) {
  if (err instanceof Telnyx.APIConnectionError) {
    console.error('Network error — check connectivity and retry');
  } else if (err instanceof Telnyx.RateLimitError) {
    const retryAfter = err.headers?.['retry-after'] || 1;
    await new Promise(r => setTimeout(r, retryAfter * 1000));
  } else if (err instanceof Telnyx.APIError) {
    console.error(`API error ${err.status}: ${err.message}`);
    if (err.status === 422) {
      console.error('Validation error — check required fields and formats');
    }
  }
}

Common error codes: 401 invalid API key, 403 insufficient permissions, 404 resource not found, 422 validation error (check field formats), 429 rate limited (retry with exponential backoff).

Important Notes

• Phone numbers must be in E.164 format (e.g., +13125550001). Include the + prefix and country code. No spaces, dashes, or parentheses.
• Pagination: List methods return an auto-paginating iterator. Use for await (const item of result) { ... } to iterate through all pages automatically.

Reference Use Rules

Do not invent Telnyx parameters, enums, response fields, or webhook fields.

• If the parameter, enum, or response field you need is not shown inline in this skill, read [references/api-details.md](references/api-details.md) before writing code.
• Before using any operation in ## Additional Operations, read [the optional-parameters section](references/api-details.md#optional-parameters) and [the response-schemas section](references/api-details.md#response-schemas).

Core Tasks

Create an assistant

Assistant creation is the entrypoint for any AI assistant integration. Agents need the exact creation method and the top-level fields returned by the SDK.

client.ai.assistants.create() — POST /ai/assistants

| Parameter | Type | Required | Description | |-----------|------|----------|-------------| | name | string | Yes | | | model | string | Yes | ID of the model to use. | | instructions | string | Yes | System instructions for the assistant. | | tools | array[object] | No | The tools that the assistant can use. | | toolIds | array[string] | No | | | description | string | No | | | ... | | | +12 optional params in [references/api-details.md](references/api-details.md) |

const assistant = await client.ai.assistants.create({
  instructions: 'You are a helpful assistant.',
  model: 'openai/gpt-4o',
  name: 'my-resource',
});

console.log(assistant.id);

Primary response fields:

• assistant.id
• assistant.name
• assistant.model
• assistant.instructions
• assistant.createdAt
• assistant.description

Chat with an assistant

Chat is the primary runtime path. Agents need the exact assistant method and the response content field.

client.ai.assistants.chat() — POST /ai/assistants/{assistant_id}/chat

| Parameter | Type | Required | Description | |-----------|------|----------|-------------| | content | string | Yes | The message content sent by the client to the assistant | | conversationId | string (UUID) | Yes | A unique identifier for the conversation thread, used to mai... | | assistantId | string (UUID) | Yes | | | name | string | No | The optional display name of the user sending the message |

const response = await client.ai.assistants.chat('assistant_id', {
  content: 'Tell me a joke about cats',
  conversation_id: '42b20469-1215-4a9a-8964-c36f66b406f4',
});

console.log(response.content);

Primary response fields:

• response.content

Create an assistant test

Test creation is the main validation path for production assistant behavior before deployment.

client.ai.assistants.tests.create() — POST /ai/assistants/tests

| Parameter | Type | Required | Description | |-----------|------|----------|-------------| | name | string | Yes | A descriptive name for the assistant test. | | destination | string | Yes | The target destination for the test conversation. | | instructions | string | Yes | Detailed instructions that define the test scenario and what... | | rubric | array[object] | Yes | Evaluation criteria used to assess the assistant's performan... | | description | string | No | Optional detailed description of what this test evaluates an... | | telnyxConversationChannel | object | No | The communication channel through which the test will be con... | | maxDurationSeconds | integer | No | Maximum duration in seconds that the test conversation shoul... | | ... | | | +1 optional params in [references/api-details.md](references/api-details.md) |

const assistantTest = await client.ai.assistants.tests.create({
  destination: '+15551234567',
  instructions:
    'Act as a frustrated customer who received a damaged product. Ask for a refund and escalate if not satisfied with the initial response.',
  name: 'Customer Support Bot Test',
  rubric: [
    { criteria: 'Assistant responds within 30 seconds', name: 'Response Time' },
    { criteria: 'Provides correct product information', name: 'Accuracy' },
  ],
});

console.log(assistantTest.test_id);

Primary response fields:

• assistantTest.testId
• assistantTest.name
• assistantTest.destination
• assistantTest.createdAt
• assistantTest.instructions
• assistantTest.description

---

Important Supporting Operations

Use these when the core tasks above are close to your flow, but you need a common variation or follow-up step.

Get an assistant

Fetch the current state before updating, deleting, or making control-flow decisions.

client.ai.assistants.retrieve() — GET /ai/assistants/{assistant_id}

| Parameter | Type | Required | Description | |-----------|------|----------|-------------| | assistantId | string (UUID) | Yes | | | callControlId | string (UUID) | No | | | fetchDynamicVariablesFromWebhook | boolean | No | | | from | string (E.164) | No | | | ... | | | +1 optional params in [references/api-details.md](references/api-details.md) |

const assistant = await client.ai.assistants.retrieve('550e8400-e29b-41d4-a716-446655440000');

console.log(assistant.id);

Primary response fields:

• assistant.id
• assistant.name
• assistant.createdAt
• assistant.description
• assistant.dynamicVariables
• assistant.dynamicVariablesWebhookUrl

Update an assistant

Create or provision an additional resource when the core tasks do not cover this flow.

client.ai.assistants.update() — POST /ai/assistants/{assistant_id}

| Parameter | Type | Required | Description | |-----------|------|----------|-------------| | assistantId | string (UUID) | Yes | | | name | string | No | | | model | string | No | ID of the model to use. | | instructions | string | No | System instructions for the assistant. | | ... | | | +16 optional params in [references/api-details.md](references/api-details.md) |

const assistant = await client.ai.assistants.update('550e8400-e29b-41d4-a716-446655440000');

console.log(assistant.id);

Primary response fields:

• assistant.id
• assistant.name
• assistant.createdAt
• assistant.description
• assistant.dynamicVariables
• assistant.dynamicVariablesWebhookUrl

List assistants

Inspect available resources or choose an existing resource before mutating it.

client.ai.assistants.list() — GET /ai/assistants

const assistantsList = await client.ai.assistants.list();

console.log(assistantsList.data);

Response wrapper:

• items: assistantsList.data

Primary item fields:

• id
• name
• createdAt
• description
• dynamicVariables
• dynamicVariablesWebhookUrl

Import assistants from external provider

Import existing assistants from an external provider instead of creating from scratch.

client.ai.assistants.imports() — POST /ai/assistants/import

| Parameter | Type | Required | Description | |-----------|------|----------|-------------| | provider | enum (elevenlabs, vapi, retell) | Yes | The external provider to import assistants from. | | apiKeyRef | string | Yes | Integration secret pointer that refers to the API key for th... | | importIds | array[string] | No | Optional list of assistant IDs to import from the external p... |

const assistantsList = await client.ai.assistants.imports({
  api_key_ref: 'api_key_ref',
  provider: 'elevenlabs',
});

console.log(assistantsList.data);

Response wrapper:

• items: assistantsList.data

Primary item fields:

• id
• name
• createdAt
• description
• dynamicVariables
• dynamicVariablesWebhookUrl

Get All Tags

Inspect available resources or choose an existing resource before mutating it.

client.ai.assistants.tags.list() — GET /ai/assistants/tags

const tags = await client.ai.assistants.tags.list();

console.log(tags.tags);

Primary response fields:

• tags.tags

List assistant tests with pagination

Inspect available resources or choose an existing resource before mutating it.

client.ai.assistants.tests.list() — GET /ai/assistants/tests

| Parameter | Type | Required | Description | |-----------|------|----------|-------------| | testSuite | string | No | Filter tests by test suite name | | telnyxConversationChannel | string | No | Filter tests by communication channel (e.g., 'web_chat', 'sm... | | destination | string | No | Filter tests by destination (phone number, webhook URL, etc.... | | ... | | | +1 optional params in [references/api-details.md](references/api-details.md) |

// Automatically fetches more pages as needed.
for await (const assistantTest of client.ai.assistants.tests.list()) {
  console.log(assistantTest.test_id);
}

Response wrapper:

• items: assistantTest.data
• pagination: assistantTest.meta

Primary item fields:

• name
• createdAt
• description
• destination
• instructions
• maxDurationSeconds

Get all test suite names

Inspect available resources or choose an existing resource before mutating it.

client.ai.assistants.tests.testSuites.list() — GET /ai/assistants/tests/test-suites

const testSuites = await client.ai.assistants.tests.testSuites.list();

console.log(testSuites.data);

Response wrapper:

• items: testSuites.data

Primary item fields:

• data

Get test suite run history

Fetch the current state before updating, deleting, or making control-flow decisions.

client.ai.assistants.tests.testSuites.runs.list() — GET /ai/assistants/tests/test-suites/{suite_name}/runs

| Parameter | Type | Required | Description | |-----------|------|----------|-------------| | suiteName | string | Yes | | | testSuiteRunId | string (UUID) | No | Filter runs by specific suite execution batch ID | | status | string | No | Filter runs by execution status (pending, running, completed... | | page | object | No | Consolidated page parameter (deepObject style). |

// Automatically fetches more pages as needed.
for await (const testRunResponse of client.ai.assistants.tests.testSuites.runs.list('suite_name')) {
  console.log(testRunResponse.run_id);
}

Response wrapper:

• items: testRunResponse.data
• pagination: testRunResponse.meta

Primary item fields:

• status
• createdAt
• updatedAt
• completedAt
• conversationId
• conversationInsightsId

---

Additional Operations

Use the core tasks above first. The operations below are indexed here with exact SDK methods and required params; use [references/api-details.md](references/api-details.md) for full optional params, response schemas, and lower-frequency webhook payloads. Before using any operation below, read [the optional-parameters section](references/api-details.md#optional-parameters) and [the response-schemas section](references/api-details.md#response-schemas) so you do not guess missing fields.

| Operation | SDK method | Endpoint | Use when | Required params | |-----------|------------|----------|----------|-----------------| | Trigger test suite execution | client.ai.assistants.tests.testSuites.runs.trigger() | POST /ai/assistants/tests/test-suites/{suite_name}/runs | Trigger a follow-up action in an existing workflow rather than creating a new top-level resource. | suiteName | | Get assistant test by ID | client.ai.assistants.tests.retrieve() | GET /ai/assistants/tests/{test_id} | Fetch the current state before updating, deleting, or making control-flow decisions. | testId | | Update an assistant test | client.ai.assistants.tests.update() | PUT /ai/assistants/tests/{test_id} | Modify an existing resource without recreating it. | testId | | Delete an assistant test | client.ai.assistants.tests.delete() | DELETE /ai/assistants/tests/{test_id} | Remove, detach, or clean up an existing resource. | testId | | Get test run history for a specific test | client.ai.assistants.tests.runs.list() | GET /ai/assistants/tests/{test_id}/runs | Fetch the current state before updating, deleting, or making control-flow decisions. | testId | | Trigger a manual test run | client.ai.assistants.tests.runs.trigger() | POST /ai/assistants/tests/{test_id}/runs | Trigger a follow-up action in an existing workflow rather than creating a new top-level resource. | testId | | Get specific test run details | client.ai.assistants.tests.runs.retrieve() | GET /ai/assistants/tests/{test_id}/runs/{run_id} | Fetch the current state before updating, deleting, or making control-flow decisions. | testId, runId | | Delete an assistant | client.ai.assistants.delete() | DELETE /ai/assistants/{assistant_id} | Remove, detach, or clean up an existing resource. | assistantId | | Get Canary Deploy | client.ai.assistants.canaryDeploys.retrieve() | GET /ai/assistants/{assistant_id}/canary-deploys | Fetch the current state before updating, deleting, or making control-flow decisions. | assistantId | | Create Canary Deploy | client.ai.assistants.canaryDeploys.create() | POST /ai/assistants/{assistant_id}/canary-deploys | Create or provision an additional resource when the core tasks do not cover this flow. | versions, assistantId | | Update Canary Deploy | client.ai.assistants.canaryDeploys.update() | PUT /ai/assistants/{assistant_id}/canary-deploys | Modify an existing resource without recreating it. | versions, assistantId | | Delete Canary Deploy | client.ai.assistants.canaryDeploys.delete() | DELETE /ai/assistants/{assistant_id}/canary-deploys | Remove, detach, or clean up an existing resource. | assistantId | | Assistant Sms Chat | client.ai.assistants.sendSMS() | POST /ai/assistants/{assistant_id}/chat/sms | Run assistant chat over SMS instead of direct API chat. | from, to, assistantId | | Clone Assistant | client.ai.assistants.clone() | POST /ai/assistants/{assistant_id}/clone | Trigger a follow-up action in an existing workflow rather than creating a new top-level resource. | assistantId | | List scheduled events | client.ai.assistants.scheduledEvents.list() | GET /ai/assistants/{assistant_id}/scheduled_events | Fetch the current state before updating, deleting, or making control-flow decisions. | assistantId | | Create a scheduled event | `client.ai.assistants.scheduledEve

…

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: team-telnyx
• Source: team-telnyx/ai
• License: MIT

Install and usage instructions live in the source repository linked above.