Workbench

Preview Workbench Ai

Run the default AI pass on the first three pending rows. CHARGES.

A preview in scope, not in price: it is the real pass and bills those rows. Only approved_max_credits and quote_expires_at are read from the body.

post/workbench/tables/{table_id}/ai/preview

Request

  • Base URL: https://be.graph8.com/api/v1
  • URL: https://be.graph8.com/api/v1/workbench/tables/{table_id}/ai/preview
  • Auth: HTTP bearer

Path parameters

table_idstring required

Workbench table id (UUID).

Headers

Authorizationstring nullable
X-Target-Org-Idstring nullable

Request body

row_idsinteger[] nullable

Rows to run. OMIT to run EVERY row in the table.

exclude_row_idsinteger[] nullable
modelstring nullable

Override the configured model.

promptstring nullable

Override the configured prompt.

status_filterstring nullable
conditionsobject[] nullable
qualification_modeboolean
multi_row_outputboolean nullable
max_rows_per_sourceinteger nullable
approved_max_creditsinteger nullable

Ceiling the caller approves. The run refuses to exceed it.

quote_expires_atstring date-time nullable
quote_idstring uuid nullable

Response

Successful Response

dataEnrichmentPayload 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.

Changes

No recorded changes to this operation across all 2 revisions of this API.