Operations
Operations

Set message SMS copy

Give take_a_message a second way out: a mobile number that receives a short SMS copy of every message the agent takes, alongside the email. Use it when a business cannot afford to miss a message, the SMS does not travel through the recipient's mail server, so a spam filter or a full mailbox cannot swallow both copies. The email stays the primary channel and is unchanged. Pass an empty mobile to turn the text copy off. The change lands on the draft version.

POST
/operations/set_take_message_sms

Authorization

bearerAuth
AuthorizationBearer <token>

A personal access token from Settings > API tokens.

In: header

Header Parameters

Idempotency-Key?string

A key you choose, such as a UUID, that makes this POST safe to retry. Within 24 hours the same key and request answers with the first successful answer and runs nothing, the same key with a different request answers 422 idempotency_key_reused, and a key whose request is still running answers 409 idempotency_key_in_use. A failed request keeps nothing, so the same key runs it again.

Length1 <= length <= 255

Request Body

application/json

TypeScript Definitions

Use the request body type in TypeScript.

Response Body

application/json

application/problem+json

application/problem+json

application/problem+json

application/problem+json

application/problem+json

application/problem+json

application/problem+json

curl -X POST "https://example.com/operations/set_take_message_sms" \  -H "Content-Type: application/json" \  -d '{    "mobile": "string",    "agent": "string"  }'
{}
{
  "type": "http://example.com",
  "title": "string",
  "status": 0,
  "detail": "string",
  "code": "string",
  "errors": [
    {
      "path": "string",
      "message": "string"
    }
  ],
  "estimate": {},
  "retryAfterSeconds": 0
}
{
  "type": "http://example.com",
  "title": "string",
  "status": 0,
  "detail": "string",
  "code": "string",
  "errors": [
    {
      "path": "string",
      "message": "string"
    }
  ],
  "estimate": {},
  "retryAfterSeconds": 0
}
{
  "type": "http://example.com",
  "title": "string",
  "status": 0,
  "detail": "string",
  "code": "string",
  "errors": [
    {
      "path": "string",
      "message": "string"
    }
  ],
  "estimate": {},
  "retryAfterSeconds": 0
}
{
  "type": "http://example.com",
  "title": "string",
  "status": 0,
  "detail": "string",
  "code": "string",
  "errors": [
    {
      "path": "string",
      "message": "string"
    }
  ],
  "estimate": {},
  "retryAfterSeconds": 0
}
{
  "type": "http://example.com",
  "title": "string",
  "status": 0,
  "detail": "string",
  "code": "string",
  "errors": [
    {
      "path": "string",
      "message": "string"
    }
  ],
  "estimate": {},
  "retryAfterSeconds": 0
}
{
  "type": "http://example.com",
  "title": "string",
  "status": 0,
  "detail": "string",
  "code": "string",
  "errors": [
    {
      "path": "string",
      "message": "string"
    }
  ],
  "estimate": {},
  "retryAfterSeconds": 0
}
{
  "type": "http://example.com",
  "title": "string",
  "status": 0,
  "detail": "string",
  "code": "string",
  "errors": [
    {
      "path": "string",
      "message": "string"
    }
  ],
  "estimate": {},
  "retryAfterSeconds": 0
}

Set message details POST

Declare the details take_a_message records on EVERY message, a property address, a job number, a date, whether or not the caller gives them. Each declared detail becomes a required argument the agent must answer during the call, and its own labelled line in the message email; one the caller will not give is recorded as "not given" instead of being left off. Use this when a team matches messages to jobs or accounts by hand, where a field they can see is workable and a field that simply is not there looks like a complete message about something else. Prefer it over wording the requirement into the system prompt: prose asks the model to remember, this asks the schema. `details` replaces the whole list; pass an empty array to turn it off. The change lands on the draft version.

Set term blocklist POST

Set the workspace's exact-match term blocklist, deterministic term blocking. Available only to a workspace whose plan includes it; the operation refuses otherwise, and enabling it is a conversation with the Vertical AI team rather than a setting. Unlike safety guardrails, which score a confidence and act above a threshold, this matches literally: a term either appears or it does not, so there is no sensitivity to set. `terms` REPLACES the whole list, send every term you want blocked, or an empty array to clear it. Each term is trimmed, empties are dropped, and duplicates are removed case-insensitively. A term may be at most 3 words and may not contain a line break, and the list is capped at 10000 entries, which is the engine's own ceiling. Use it for a specific, enumerable list the business must never say: competitor names, a claim its legal team has not cleared, a term a regulator has asked it to stop using. Do NOT use it to steer a topic. Exact matching has no sense of context and the failure is silent, a dental practice that blocks "extraction" has stopped its agent discussing the procedure it books most, and nobody finds out until bookings fall. Topics belong in the system prompt, where the model can weigh them in context.