Create AIPrompt

Create a new AI prompt, optionally continuing an existing AI conversation from a previous prompt.

When creating an AIPrompt via this service, the API persists the user message as an AI message , creates an AI conversation automatically when conversation_id is omitted, and returns the user's and assistant's created AI messages together with any assets generated (e.g. a visualization item). Exactly one text input is required; optional dataset inputs are linked in the background as dataset/securable associations on the created user message, and optional item or dashboard inputs are persisted in the background as AIMessageAsset associations on that message so they can be retrieved later. Generated dashboards (and items in a dashboard) can be optionally saved as new dashboards or by updating existing dashboards .

Agents

• item : generate, suggest, or describe a single Luzmo item (chart). Supports task: "generate" | "suggest" | "describe" .

• (*) analyst : IQ-backed data analysis that answers natural-language questions about your data (in text and/or with a visualization item). Only supports task: "generate" .

• (*) dashboard : generate or edit a multi-view dashboard composed of multiple items. Only supports task: "generate" , and does not support response_mode: "text" . Pass an optional { type: "dashboard" } input to provide the current dashboard state (views, items, theme, name) and an optional current_screen_mode so the agent edits the right view.

(*) Requires the Luzmo IQ addon to be included in your license.

Streaming response

Set stream: true in the request properties to receive progress, text, and asset events as they are produced instead of waiting for the full result. The endpoint supports two transports:

• HTTP (Server-Sent Events) : the response is sent with Content-Type: text/event-stream; charset=utf-8 , Cache-Control: no-cache, no-transform , Connection: keep-alive , and Transfer-Encoding: chunked . Each event is delivered as a single data: {...} frame, and the stream ends with a final data: [DONE] frame before the connection closes.

• Socket.IO : connected socket clients receive the same JSON event objects on the aiprompt channel. The socket transport is used automatically when a socket is connected to the API and the same aiprompt.create payload is sent.

Every event emitted contains a type , and after the first event also the streaming context fields conversation_id , user_message_id , and assistant_message_id . A typical stream produces events in this order:

1. start event is emitted once after the user message has been persisted.

2. Zero or more progress events while the workflow is running.

3. For each assistant text block: text_start → one or more text_delta → text_end .

4. For each generated asset: asset_start → one or more asset_delta → asset_end .

5. Optionally an error event if the workflow fails.

6. A final finish event whose result matches the non-streaming response (or null if the workflow failed).

See the "Streaming response" schema below for the exact payload of every event type, and the streamed example for a complete ordered sequence.