Create Ai Column · ZeroReach Docs

Add a column defined by a prompt to the leads or companies table (RO-340). Nothing runs until a member runs it on rows. At most 10 per table (409 `ai_columns_limit`); `options` only for `classify` (2-12, 422 `options_required` / `options_not_allowed`).

API key access

Needs the leads:write scope with an API key (ro_pat_...). A signed-in session uses the caller's role.

POST/api/v1/ai-columns

Authorization

AuthorizationBearer <token>

Access token from /api/v1/auth/login, or an API key (ro_pat_..., RO-176) from /api/v1/workspaces/current/api-keys: the key implies its workspace and needs the route's scope. MCP connectors (/api/v1/mcp only) may use an OAuth access token (ro_oat_..., RO-284).

In: header

Header Parameters

X-Workspace-Id?string | null

Id of the workspace to act on (must be a member).

Request Body

entitystring

lead or company.

namestring

Length1 <= length <= 80

promptstring

What to find out for each row, e.g. "Does this company sell to dentists?".

Length3 <= length <= 2000

kind?string | null

text (default), classify or score.

options?array<string> | null

The labels a classify column picks from (2-12; only for classify).

Itemsitems <= 12

Response Body

curl -X POST "http://localhost:8000/api/v1/ai-columns" \
  -H "X-Workspace-Id: string" \
  -H "Content-Type: application/json" \
  -d '{
    "entity": "string",
    "name": "string",
    "prompt": "string"
  }'

curl -X POST "http://localhost:8000/api/v1/ai-columns" \  -H "X-Workspace-Id: string" \  -H "Content-Type: application/json" \  -d '{    "entity": "string",    "name": "string",    "prompt": "string"  }'

{
  "id": "497f6eca-6276-4993-bfeb-53cbbbba6f08",
  "entity": "string",
  "name": "string",
  "prompt": "string",
  "kind": "string",
  "options": [
    "string"
  ],
  "created_by": "ee824cad-d7a6-4f48-87dc-e8461a9201c4",
  "created_at": "2019-08-24T14:15:22Z",
  "updated_at": "2019-08-24T14:15:22Z",
  "cells": {
    "pending": 0,
    "running": 0,
    "done": 0,
    "failed": 0
  },
  "credits": 0
}

Empty

{
  "detail": [
    {
      "loc": [
        "string"
      ],
      "msg": "string",
      "type": "string",
      "input": null,
      "ctx": {}
    }
  ]
}