---
title: "Draft machine checks from plain words"
method: POST
path: "/v1/check/draft"
tags: ["Received-work checks"]
---

# Draft machine checks from plain words

`POST /v1/check/draft`

## Request

- Base URL: `https://www.licium.ai`
- URL: `https://www.licium.ai/v1/check/draft`
- Auth: none required

Anonymous. Turns plain-word requirements into editable machine checks, the same drafting that POST /v1/check applies to need. Reads only the words and optional column names, never a delivery. Produces no verdict and does not use the free check allowance. The suggested_criterion sentences from a previous report are kept verbatim. Send the returned checks to POST /v1/check as criteria (check_id as checkId, blocking true). 30 drafts per minute per address.

## Request body

- object
  - `need` string, required
  - `columns` string[]

## Response `200`

Up to 12 drafted checks.

- object
  - `success` boolean
  - `data` object
    - `criteria` object[]
      - `check_id` string
      - `kind` string
      - `label` string
      - `params` object
    - `drafted_by` 'model' | 'rules'

## Other responses

- `400`: No words, or the body is not JSON.
- `413`: Body over 32 KiB.
- `429`: Too many drafts in a row.

---

[API](https://skmtc.dev/licium/apis/licium-public-api.md) · [All operations](https://skmtc.dev/licium/apis/licium-public-api/llms.txt) · [OpenAPI document](https://skmtc.dev/licium/apis/licium-public-api/revisions/d91a72f755f4?raw)