Ai telnyx-ai-assistants-curl
git clone https://github.com/team-telnyx/ai
T=$(mktemp -d) && git clone --depth=1 https://github.com/team-telnyx/ai "$T" && mkdir -p ~/.claude/skills && cp -r "$T/providers/cursor/plugin/skills/telnyx-ai-assistants-curl" ~/.claude/skills/team-telnyx-ai-telnyx-ai-assistants-curl-15d042 && rm -rf "$T"
providers/cursor/plugin/skills/telnyx-ai-assistants-curl/SKILL.mdTelnyx AI Assistants - curl
Installation
# curl is pre-installed on macOS, Linux, and Windows 10+
Setup
export TELNYX_API_KEY="YOUR_API_KEY_HERE"
All examples below use
$TELNYX_API_KEY for authentication.
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:
curl \ -X POST \ -H "Authorization: Bearer $TELNYX_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "name": "my-resource", "model": "openai/gpt-4o", "instructions": "You are a helpful assistant." }' \ "https://api.telnyx.com/v2/ai/assistants"
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.,
). Include the+13125550001
prefix and country code. No spaces, dashes, or parentheses.+ - Pagination: List endpoints return paginated results. Use
andpage[number]
query parameters to navigate pages. Checkpage[size]
in the response.meta.total_pages
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 before writing code.
- Before using any operation in
, read the optional-parameters section and the response-schemas section.## Additional Operations
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.
POST /ai/assistants
| Parameter | Type | Required | Description |
|---|---|---|---|
| string | Yes | |
| string | Yes | ID of the model to use. |
| string | Yes | System instructions for the assistant. |
| array[object] | No | The tools that the assistant can use. |
| array[string] | No | |
| string | No | |
| ... | +12 optional params in references/api-details.md |
curl \ -X POST \ -H "Authorization: Bearer $TELNYX_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "name": "my-resource", "model": "openai/gpt-4o", "instructions": "You are a helpful assistant." }' \ "https://api.telnyx.com/v2/ai/assistants"
Primary response fields:
.data.id.data.name.data.model.data.instructions.data.created_at.data.description
Chat with an assistant
Chat is the primary runtime path. Agents need the exact assistant method and the response content field.
POST /ai/assistants/{assistant_id}/chat
| Parameter | Type | Required | Description |
|---|---|---|---|
| string | Yes | The message content sent by the client to the assistant |
| string (UUID) | Yes | A unique identifier for the conversation thread, used to mai... |
| string (UUID) | Yes | |
| string | No | The optional display name of the user sending the message |
curl \ -X POST \ -H "Authorization: Bearer $TELNYX_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "content": "Tell me a joke about cats", "conversation_id": "42b20469-1215-4a9a-8964-c36f66b406f4" }' \ "https://api.telnyx.com/v2/ai/assistants/550e8400-e29b-41d4-a716-446655440000/chat"
Primary response fields:
.data.content
Create an assistant test
Test creation is the main validation path for production assistant behavior before deployment.
POST /ai/assistants/tests
| Parameter | Type | Required | Description |
|---|---|---|---|
| string | Yes | A descriptive name for the assistant test. |
| string | Yes | The target destination for the test conversation. |
| string | Yes | Detailed instructions that define the test scenario and what... |
| array[object] | Yes | Evaluation criteria used to assess the assistant's performan... |
| string | No | Optional detailed description of what this test evaluates an... |
| object | No | The communication channel through which the test will be con... |
| integer | No | Maximum duration in seconds that the test conversation shoul... |
| ... | +1 optional params in references/api-details.md |
curl \ -X POST \ -H "Authorization: Bearer $TELNYX_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "name": "Customer Support Bot Test", "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.", "rubric": [ { "criteria": "Assistant responds within 30 seconds", "name": "Response Time" }, { "criteria": "Provides correct product information", "name": "Accuracy" } ] }' \ "https://api.telnyx.com/v2/ai/assistants/tests"
Primary response fields:
.data.test_id.data.name.data.destination.data.created_at.data.instructions.data.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.
GET /ai/assistants/{assistant_id}
| Parameter | Type | Required | Description |
|---|---|---|---|
| string (UUID) | Yes | |
| string (UUID) | No | |
| boolean | No | |
| string (E.164) | No | |
| ... | +1 optional params in references/api-details.md |
curl -H "Authorization: Bearer $TELNYX_API_KEY" "https://api.telnyx.com/v2/ai/assistants/550e8400-e29b-41d4-a716-446655440000"
Primary response fields:
.data.id.data.name.data.created_at.data.description.data.dynamic_variables.data.dynamic_variables_webhook_url
Update an assistant
Create or provision an additional resource when the core tasks do not cover this flow.
POST /ai/assistants/{assistant_id}
| Parameter | Type | Required | Description |
|---|---|---|---|
| string (UUID) | Yes | |
| string | No | |
| string | No | ID of the model to use. |
| string | No | System instructions for the assistant. |
| ... | +16 optional params in references/api-details.md |
curl \ -X POST \ -H "Authorization: Bearer $TELNYX_API_KEY" \ -H "Content-Type: application/json" \ "https://api.telnyx.com/v2/ai/assistants/550e8400-e29b-41d4-a716-446655440000"
Primary response fields:
.data.id.data.name.data.created_at.data.description.data.dynamic_variables.data.dynamic_variables_webhook_url
List assistants
Inspect available resources or choose an existing resource before mutating it.
GET /ai/assistants
curl -H "Authorization: Bearer $TELNYX_API_KEY" "https://api.telnyx.com/v2/ai/assistants"
Response wrapper:
- items:
.data
Primary item fields:
idnamecreated_atdescriptiondynamic_variablesdynamic_variables_webhook_url
Import assistants from external provider
Import existing assistants from an external provider instead of creating from scratch.
POST /ai/assistants/import
| Parameter | Type | Required | Description |
|---|---|---|---|
| enum (elevenlabs, vapi, retell) | Yes | The external provider to import assistants from. |
| string | Yes | Integration secret pointer that refers to the API key for th... |
| array[string] | No | Optional list of assistant IDs to import from the external p... |
curl \ -X POST \ -H "Authorization: Bearer $TELNYX_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "provider": "elevenlabs", "api_key_ref": "my-openai-key" }' \ "https://api.telnyx.com/v2/ai/assistants/import"
Response wrapper:
- items:
.data
Primary item fields:
idnamecreated_atdescriptiondynamic_variablesdynamic_variables_webhook_url
Get All Tags
Inspect available resources or choose an existing resource before mutating it.
GET /ai/assistants/tags
curl -H "Authorization: Bearer $TELNYX_API_KEY" "https://api.telnyx.com/v2/ai/assistants/tags"
Primary response fields:
.data.tags
List assistant tests with pagination
Inspect available resources or choose an existing resource before mutating it.
GET /ai/assistants/tests
| Parameter | Type | Required | Description |
|---|---|---|---|
| string | No | Filter tests by test suite name |
| string | No | Filter tests by communication channel (e.g., 'web_chat', 'sm... |
| string | No | Filter tests by destination (phone number, webhook URL, etc.... |
| ... | +1 optional params in references/api-details.md |
curl -H "Authorization: Bearer $TELNYX_API_KEY" "https://api.telnyx.com/v2/ai/assistants/tests"
Response wrapper:
- items:
.data - pagination:
.meta
Primary item fields:
namecreated_atdescriptiondestinationinstructionsmax_duration_seconds
Get all test suite names
Inspect available resources or choose an existing resource before mutating it.
GET /ai/assistants/tests/test-suites
curl -H "Authorization: Bearer $TELNYX_API_KEY" "https://api.telnyx.com/v2/ai/assistants/tests/test-suites"
Response wrapper:
- items:
.data
Primary item fields:
data
Get test suite run history
Fetch the current state before updating, deleting, or making control-flow decisions.
GET /ai/assistants/tests/test-suites/{suite_name}/runs
| Parameter | Type | Required | Description |
|---|---|---|---|
| string | Yes | |
| string (UUID) | No | Filter runs by specific suite execution batch ID |
| string | No | Filter runs by execution status (pending, running, completed... |
| object | No | Consolidated page parameter (deepObject style). |
curl -H "Authorization: Bearer $TELNYX_API_KEY" "https://api.telnyx.com/v2/ai/assistants/tests/test-suites/{suite_name}/runs"
Response wrapper:
- items:
.data - pagination:
.meta
Primary item fields:
statuscreated_atupdated_atcompleted_atconversation_idconversation_insights_id
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 for full optional params, response schemas, and lower-frequency webhook payloads. Before using any operation below, read the optional-parameters section and the response-schemas section so you do not guess missing fields.
| Operation | SDK method | Endpoint | Use when | Required params |
|---|---|---|---|---|
| Trigger test suite execution | HTTP only | | Trigger a follow-up action in an existing workflow rather than creating a new top-level resource. | |
| Get assistant test by ID | HTTP only | | Fetch the current state before updating, deleting, or making control-flow decisions. | |
| Update an assistant test | HTTP only | | Modify an existing resource without recreating it. | |
| Delete an assistant test | HTTP only | | Remove, detach, or clean up an existing resource. | |
| Get test run history for a specific test | HTTP only | | Fetch the current state before updating, deleting, or making control-flow decisions. | |
| Trigger a manual test run | HTTP only | | Trigger a follow-up action in an existing workflow rather than creating a new top-level resource. | |
| Get specific test run details | HTTP only | | Fetch the current state before updating, deleting, or making control-flow decisions. | , |
| Delete an assistant | HTTP only | | Remove, detach, or clean up an existing resource. | |
| Get Canary Deploy | HTTP only | | Fetch the current state before updating, deleting, or making control-flow decisions. | |
| Create Canary Deploy | HTTP only | | Create or provision an additional resource when the core tasks do not cover this flow. | , |
| Update Canary Deploy | HTTP only | | Modify an existing resource without recreating it. | , |
| Delete Canary Deploy | HTTP only | | Remove, detach, or clean up an existing resource. | |
| Assistant Sms Chat | HTTP only | | Run assistant chat over SMS instead of direct API chat. | , , |
| Clone Assistant | HTTP only | | Trigger a follow-up action in an existing workflow rather than creating a new top-level resource. | |
| List scheduled events | HTTP only | | Fetch the current state before updating, deleting, or making control-flow decisions. | |
| Create a scheduled event | HTTP only | | Create or provision an additional resource when the core tasks do not cover this flow. | , , , , +1 more |
| Get a scheduled event | HTTP only | | Fetch the current state before updating, deleting, or making control-flow decisions. | , |
| Delete a scheduled event | HTTP only | | Remove, detach, or clean up an existing resource. | , |
| Add Assistant Tag | HTTP only | | Create or provision an additional resource when the core tasks do not cover this flow. | , |
| Remove Assistant Tag | HTTP only | | Remove, detach, or clean up an existing resource. | , |
| Get assistant texml | HTTP only | | Fetch the current state before updating, deleting, or making control-flow decisions. | |
| Add Assistant Tool | HTTP only | | Modify an existing resource without recreating it. | , |
| Remove Assistant Tool | HTTP only | | Remove, detach, or clean up an existing resource. | , |
| Test Assistant Tool | HTTP only | | Trigger a follow-up action in an existing workflow rather than creating a new top-level resource. | , |
| Get all versions of an assistant | HTTP only | | Fetch the current state before updating, deleting, or making control-flow decisions. | |
| Get a specific assistant version | HTTP only | | Fetch the current state before updating, deleting, or making control-flow decisions. | , |
| Update a specific assistant version | HTTP only | | Create or provision an additional resource when the core tasks do not cover this flow. | , |
| Delete a specific assistant version | HTTP only | | Remove, detach, or clean up an existing resource. | , |
| Promote an assistant version to main | HTTP only | | Trigger a follow-up action in an existing workflow rather than creating a new top-level resource. | , |
| List MCP Servers | HTTP only | | Inspect available resources or choose an existing resource before mutating it. | None |
| Create MCP Server | HTTP only | | Create or provision an additional resource when the core tasks do not cover this flow. | , , |
| Get MCP Server | HTTP only | | Fetch the current state before updating, deleting, or making control-flow decisions. | |
| Update MCP Server | HTTP only | | Modify an existing resource without recreating it. | |
| Delete MCP Server | HTTP only | | Remove, detach, or clean up an existing resource. | |
| List Tools | HTTP only | | Inspect available resources or choose an existing resource before mutating it. | None |
| Create Tool | HTTP only | | Create or provision an additional resource when the core tasks do not cover this flow. | , |
| Get Tool | HTTP only | | Fetch the current state before updating, deleting, or making control-flow decisions. | |
| Update Tool | HTTP only | | Modify an existing resource without recreating it. | |
| Delete Tool | HTTP only | | Remove, detach, or clean up an existing resource. | |
For exhaustive optional parameters, full response schemas, and complete webhook payloads, see references/api-details.md.