curl --request POST \
  --url https://openapi.enginy.ai/v1/ai-variables \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --data '
{
  "name": "iceBreaker",
  "entity": "CONTACT",
  "prompt": "Write a short ice breaker using {firstName}, {jobTitle}, {company}, and {lastLinkedInPost}.",
  "outputSchema": {
    "type": "text",
    "provideExplanation": true
  },
  "search": true
}
'

{
  "message": "<string>",
  "data": {
    "id": 123,
    "name": "<string>",
    "prompt": "<string>",
    "model": "<string>",
    "outputSchema": {
      "values": [
        "<string>"
      ],
      "provideExplanation": true,
      "jsonSchema": "<string>"
    },
    "search": true,
    "folderId": 123,
    "customWebsiteField": "<string>",
    "description": "<string>",
    "isPublic": true,
    "archivedAt": "2023-11-07T05:31:56Z",
    "createdAt": "2023-11-07T05:31:56Z",
    "updatedAt": "2023-11-07T05:31:56Z"
  }
}

AI Variables

Create an AI variable

Create a new AI variable in the public/manual model. Prompt placeholders must come from the relevant fields endpoint output for this workspace; generic conversation placeholders such as previousMessage are not supported here.

Enginy automatically converts prompt into the internal editor format used by the platform.

Use the contact/company fields endpoints as the source of truth for prompt placeholders. Do not assume campaign-only aliases like previousMessage are valid in manual/public AI-variable creation.

Required scope: AI_VARIABLES_WRITE

Rate limit: 30 requests per minute

POST

/

v1

/

ai-variables

curl --request POST \
  --url https://openapi.enginy.ai/v1/ai-variables \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --data '
{
  "name": "iceBreaker",
  "entity": "CONTACT",
  "prompt": "Write a short ice breaker using {firstName}, {jobTitle}, {company}, and {lastLinkedInPost}.",
  "outputSchema": {
    "type": "text",
    "provideExplanation": true
  },
  "search": true
}
'

{
  "message": "<string>",
  "data": {
    "id": 123,
    "name": "<string>",
    "prompt": "<string>",
    "model": "<string>",
    "outputSchema": {
      "values": [
        "<string>"
      ],
      "provideExplanation": true,
      "jsonSchema": "<string>"
    },
    "search": true,
    "folderId": 123,
    "customWebsiteField": "<string>",
    "description": "<string>",
    "isPublic": true,
    "archivedAt": "2023-11-07T05:31:56Z",
    "createdAt": "2023-11-07T05:31:56Z",
    "updatedAt": "2023-11-07T05:31:56Z"
  }
}

Authorizations

x-api-key

string

header

required

Body

application/json

name

string

required

Unique AI variable name.

Minimum string length: 1

prompt

string

required

Prompt template. Reference entity fields with {fieldName} placeholders. Use GET /v1/contacts/fields or GET /v1/companies/fields to discover the valid placeholder names for this workspace. Unsupported generic placeholders such as {previousMessage} are rejected in manual/public AI-variable creation.

Minimum string length: 1

entity

enum<string>

required

Entity that will store the generated value.

Available options:

CONTACT,

COMPANY

model

string | null

Optional model ID. Defaults to Enginy’s default AI model.

outputSchema

object

Optional output contract. Defaults to { "type": "text", "provideExplanation": false }.

Show child attributes

search

boolean

default:false

Enable Deep Search for this AI variable. Defaults to false.

folderId

integer | null

Optional folder ID.

customWebsiteField

string | null

Optional custom website field source.

Response

AI variable created successfully

status

enum<string>

required

Available options:

success

message

string

required

data

object

required

Show child attributes

List AI variables Get an AI variable