---
title: "Generate Workbench Prompt"
method: POST
path: "/workbench/tables/{table_id}/ai/generate-prompt"
tags: ["Workbench"]
---

# Generate Workbench Prompt

`POST /workbench/tables/{table_id}/ai/generate-prompt`

## Request

- Base URL: `https://be.graph8.com/api/v1`
- URL: `https://be.graph8.com/api/v1/workbench/tables/{table_id}/ai/generate-prompt`
- Auth: HTTP bearer

Draft an AI prompt from this table's columns. COSTS AN AI CALL.

A model reads the column names and five sample rows and writes a prompt for
you. It does not debit the credit balance, but it is a real model call, so
it is not free to run in a loop.

The returned prompt is a draft: nothing is configured and nothing is
enriched until you save it.

## Path parameters

- `table_id` string, required: Workbench table id (UUID).

## Headers

- `Authorization` string, nullable
- `X-Target-Org-Id` string, nullable

## Request body

- StagingPromptGeneratorRequest: Ask the model to write a prompt from the table's columns and sample rows.
  - `task_description` string, required: What the AI pass should do, in plain words.

## Response `200`

Successful Response

- ApiResponseEnrichmentPayload
  - `data` EnrichmentPayload, required: One enrichment object, open-shaped. Open on purpose: a workbench column set is defined by the CUSTOMER at runtime, and the enrichment result shapes grow with every provider added. Pinning them would drop whatever a provider returned that this contract had not caught up on, which on an enrichment surface is the data the customer paid for.
  - `pagination` PaginationMeta
    - `page` integer, required: Current page number (1-indexed)
    - `limit` integer, required: Items per page
    - `total` integer, required: Total number of items
    - `has_next` boolean, required: Whether there are more pages
    - `next_cursor` string, nullable: Opaque cursor for the next page; null when there are no more items. Pass it back as the `cursor` query param to fetch the following page without computing page numbers.
    - `total_available` integer, nullable: Search endpoints only: how many records really match, when known. Can be larger than `total`, which is capped at the 10,000 results that can be paged. For company search this is a distinct-company estimate. Null when unknown; absent outside search.
    - `total_is_lower_bound` boolean, nullable: Search endpoints only: true when more records match than `total` shows (the result set is larger than the 10,000 results that can be paged). Absent outside search.
    - `notes` string[], nullable: Search endpoints only: plain-language notes about the result, e.g. that more records match than can be paged, or that a reversed `between` range was put in order.

## Other responses

- `422`: Validation Error

---

[API](https://skmtc.dev/graph8/apis/graph8-developer-api.md) · [All operations](https://skmtc.dev/graph8/apis/graph8-developer-api/llms.txt) · [OpenAPI document](https://skmtc.dev/graph8/apis/graph8-developer-api/revisions/89fc11143b70?raw)
