Skip to Content
HallolaraDocs
Public APIPrompts

Update a prompt

PATCH
/prompts/{prompt_id}

Authorization

bearerAuth
headerAuthorizationBearer <token>

API key in the Authorization: Bearer <key> header. Keys are created in the Hallolara dashboard (Settings → API Keys).

Path Parameters

prompt_id*string
Match^[a-f0-9]{24}$

Request Body

application/json
  1. body

Partial update - include only the fields you want to change.

Properties1 <= properties
name?string
Length1 <= length <= 200
prompt?string
Length1 <= length <= 100000
description?string
Lengthlength <= 2000

Response Body

Updated.

application/json
  1. response
data?

A reusable assistant prompt. When automated prompt rating is enabled, every save is rated. The rating fields (health_score, approved, feedback, rated_at, rating_status) are read-only - create/update requests reject them - and follow one of these rating_status lifecycles:

  • Blocking defect: null → "rated" immediately, with health_score: 0, approved: false and feedback.
  • Otherwise: null → "pending" → "rated" or "failed".

When changed prompt content enters "pending", stale rating fields are cleared instead of being shown for the new content. On "failed", all rating fields except rating_status are cleared - the next save enqueues a fresh attempt. When rating is disabled, rating_status, health_score, approved, and rated_at remain null, and feedback remains an empty string.

Example Request
curl -X PATCH 'https://api.hallolara.ai/api/v1/prompts/65f8fa6f1a9d8e0012ab34cd' \  -H 'Content-Type: application/json' \  -d '{  "description": "Reception prompt for inbound customer calls."}'
Example Response
{  "data": {    "id": "string",    "name": "string",    "description": "string",    "prompt": "string",    "type": "answering",    "created_at": "2019-08-24T14:15:22Z",    "updated_at": "2019-08-24T14:15:22Z",    "health_score": 0,    "approved": true,    "feedback": "string",    "rated_at": "2019-08-24T14:15:22Z",    "rating_status": null  }}