> ## Documentation Index > Fetch the complete documentation index at: https://docs.periskope.app/llms.txt > Use this file to discover all available pages before exploring further. # Trigger AI Reply > Queues the org AI agent to reply to a message in a chat. Asynchronous — 200 means the run was accepted, not sent. Requires the AI agent to be available and enabled for the org and allowed in the chat. ## OpenAPI ````yaml api-reference/openapi-generated.json POST /v1/ai/reply openapi: 3.0.3 info: title: Periskope API version: 1.0.0 description: >- Periskope external API. Responses use a flat, unwrapped shape: most endpoints return the resource at the top level, and list endpoints return a wrapper object with pagination inline (e.g. `{ from, to, count, chats: [...] }`). The documented response schemas describe these shapes directly. servers: - url: https://api.periskope.app security: - bearerAuth: [] paths: /v1/ai/reply: post: tags: - AI summary: Trigger an AI reply description: >- Queues the org AI agent to reply to a message in a chat. Asynchronous — 200 means the run was accepted, not sent. Requires the AI agent to be available and enabled for the org and allowed in the chat. operationId: triggerAiReply requestBody: content: application/json: schema: type: object properties: chat_id: type: string minLength: 1 description: >- Id of the chat the AI agent should reply in — an individual chat (countrycode + number followed by @c.us, e.g. 911111111111@c.us) or a group chat (id followed by @g.us). example: 120363000000000000@g.us unique_id: type: string minLength: 1 description: >- Unique id of the message the AI agent should reply to, as returned in the unique_id field of message records. The generated reply is sent as a reply to this message. example: 3B35D00FB468D3XE3XBX org_phone: type: string minLength: 1 description: >- Org phone the AI agent should reply from, in WhatsApp server format: country code + number followed by @c.us (e.g. 911111111111@c.us). Must be a phone connected to the org. example: 911111111111@c.us required: - chat_id - unique_id - org_phone responses: '200': description: The AI reply run was queued content: application/json: schema: type: object properties: success: type: boolean enum: - true description: Always true when the AI reply run was queued message: type: string description: Human-readable confirmation message example: AI reply triggered trace_id: type: string description: >- Trace id (UUID) assigned to the queued AI reply run. Use it to correlate the run in logs and when reporting issues — the 200 response only confirms the run was queued, not that the reply was sent. example: 00000000-0000-0000-0000-000000000000 examples: default: summary: Response body value: success: true message: AI reply triggered trace_id: 00000000-0000-0000-0000-000000000000 '400': description: >- AI agent unavailable: the org is not eligible (inactive subscription, or a non-Pro plan without a free trial), the AI agent is disabled in the org settings, or the agent is not allowed on this chat content: application/json: examples: error: summary: >- AI agent unavailable: the org is not eligible (inactive subscription, or a non-Pro plan without a free trial), the AI agent is disabled in the org settings, or the agent is not allowed on this chat value: code: ERROR message: >- AI agent unavailable: the org is not eligible (inactive subscription, or a non-Pro plan without a free trial), the AI agent is disabled in the org settings, or the agent is not allowed on this chat status: 400 schema: type: object properties: code: type: string example: ERROR message: type: string example: >- AI agent unavailable: the org is not eligible (inactive subscription, or a non-Pro plan without a free trial), the AI agent is disabled in the org settings, or the agent is not allowed on this chat status: type: integer example: 400 example: code: ERROR message: >- AI agent unavailable: the org is not eligible (inactive subscription, or a non-Pro plan without a free trial), the AI agent is disabled in the org settings, or the agent is not allowed on this chat status: 400 '401': description: Invalid, expired or missing API token content: application/json: examples: error: summary: Invalid, expired or missing API token value: code: UNAUTHORIZED_ERROR message: Invalid bearer auth token status: 401 schema: type: object properties: code: type: string example: UNAUTHORIZED_ERROR message: type: string example: Invalid bearer auth token status: type: integer example: 401 example: code: UNAUTHORIZED_ERROR message: Invalid bearer auth token status: 401 '422': description: Request validation failed content: application/json: examples: error: summary: Request validation failed value: code: VALIDATION_ERROR message: Request validation failed status: 422 fields: body.chat_id: message: chat_id is required schema: type: object properties: code: type: string example: VALIDATION_ERROR message: type: string example: Request validation failed status: type: integer example: 422 fields: type: object additionalProperties: type: object properties: message: type: string value: {} example: body.chat_id: message: chat_id is required example: code: VALIDATION_ERROR message: Request validation failed status: 422 fields: body.chat_id: message: chat_id is required '429': description: Rate limit exceeded content: application/json: examples: error: summary: Rate limit exceeded value: code: RATE_LIMIT_ERROR message: You can only make 100 requests per second status: 429 schema: type: object properties: code: type: string example: RATE_LIMIT_ERROR message: type: string example: You can only make 100 requests per second status: type: integer example: 429 example: code: RATE_LIMIT_ERROR message: You can only make 100 requests per second status: 429 '500': description: Internal server error content: application/json: examples: error: summary: Internal server error value: code: UNKNOWN_ERROR message: Internal server error status: 500 schema: type: object properties: code: type: string example: UNKNOWN_ERROR message: type: string example: Internal server error status: type: integer example: 500 example: code: UNKNOWN_ERROR message: Internal server error status: 500 security: - bearerAuth: [] x-codeSamples: - lang: typescript label: TypeScript source: |- import { PeriskopeApi } from '@periskope/periskope-client'; const client = new PeriskopeApi({ authToken: 'YOUR_API_KEY', }); async function main() { const response = await client.ai.triggerAiReply({ chat_id: '120363000000000000@g.us', unique_id: '3B35D00FB468D3XE3XBX', org_phone: '911111111111@c.us', }); console.log(response); } main(); - lang: bash label: cURL source: |- curl -X POST 'https://api.periskope.app/v1/ai/reply' \ -H 'Authorization: Bearer YOUR_API_KEY' \ -H 'Content-Type: application/json' \ -d '{ "chat_id": "120363000000000000@g.us", "unique_id": "3B35D00FB468D3XE3XBX", "org_phone": "911111111111@c.us" }' components: securitySchemes: bearerAuth: type: http scheme: bearer description: >- Your Periskope API token, sent as `Authorization: Bearer `. Generate one from the Periskope dashboard under **Settings → API & Webhooks**. API access requires an active Pro or Enterprise plan. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.