POST
/
training
Create a custom training
curl --request POST \
  --url https://api.open.cx/training \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "title": "<string>",
  "answer": "<string>"
}'
{
  "id": "<string>",
  "organization_id": "<string>",
  "question": "<string>",
  "answer": "<string>",
  "is_draft": true,
  "accepted_by": 123,
  "draft_payload": "<any>",
  "learned_from_session_id": "<string>",
  "type": "BEHAVIORAL",
  "restricted_to_channels": [
    "web"
  ],
  "created_at": "<string>",
  "updated_at": "<string>",
  "directory_id": "<string>"
}

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json
​
title
string
required

The title or question for the custom training. This serves as the prompt or situation that the AI will be trained to recognize. It should be clear and concise, ideally framed as a question or scenario.

Minimum length: 3
​
answer
string
required

The answer content for the custom training. This is the response that the AI should provide when it encounters a question or situation similar to the one defined in the title field. It should be comprehensive and provide the information needed to address the scenario.

Minimum length: 10

Response

Returns the created custom training

​
id
string
required
​
organization_id
string
required
​
question
string
required
​
answer
string
required
​
is_draft
boolean
required
​
accepted_by
number | null
required
​
learned_from_session_id
string | null
required
​
type
enum<string>
required
Available options:
BEHAVIORAL,
SCENARIO_SPECIFIC
​
restricted_to_channels
enum<string>[]
required
​
created_at
string
required
​
updated_at
string
required
​
directory_id
string | null
required
​
draft_payload
any

Draft payload with structured data