---
title: "Save Ai Enrichment Config"
method: POST
path: "/enrichment/ai/configs"
tags: ["Enrichment"]
---

# Save Ai Enrichment Config

`POST /enrichment/ai/configs`

## Request

- Base URL: `https://be.graph8.com/api/v1`
- URL: `https://be.graph8.com/api/v1/enrichment/ai/configs`
- Auth: HTTP bearer

Create an AI enrichment group on a list. FREE - saving never runs.

PLURAL, matching the `GET /enrichment/ai/configs` that already ships. The
app spells this one `/ai/config`; publishing both would be two paths one
letter apart.

`config.is_global` true - the app's DEFAULT - makes the group apply to
EVERY list in the organisation, not just `config.list_id`. That is the
wider blast radius of the two and it is what you get by omission, so set it
deliberately.

A `config.group_id` naming a qualification group shared by every list (the
ICP and Persona qualification groups) answers 409 with code
`shared_qualification_group`: those groups cannot gain columns here.

## Headers

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

## Request body

- SaveAIConfigRequest: Save an AI enrichment group. Saving costs nothing; running it does.
  - `config` AIEnrichmentConfigDto, required: A full AI enrichment group definition.
    - `id` string, uuid, nullable
    - `group_id` string, nullable
    - `name` string, nullable
    - `description` string, nullable
    - `input_mapping` string[], required
    - `prompt` string, required
    - `config` AIConfigDto, required: Execution settings for an AI enrichment group.
      - `auto_update` boolean: Re-run when new data arrives. ONGOING SPEND when true.
      - `run_condition` string, nullable
      - `scope` 'company' | 'contact' | 'combined', nullable
      - `use_advanced_search` boolean
      - `use_json` boolean
      - `list_routing` ListRoutingDto: Route records to different lists based on an AI output field.
        - `enabled` boolean
        - `field_name` string
        - `list_mappings` object
      - `skip_existing_values` boolean: Skip rows that already have a value - the main cost control.
      - `skip_recently_enriched` boolean: Skip rows enriched in the last 30 days.
      - `mode` 'standard' | 'find_people'
      - `find_people` AIFindPeopleSettingsDto: Find-people mode settings for an AI group.
        - `max_people` integer
        - `destination_table_id` string, nullable
        - `destination_table_name` string, nullable
        - `export_mode` 'auto' | 'review': `auto` exports found contacts without a human step; `review` holds them.
        - `review_store` 'source_metadata'
    - `model` string, required
    - `usecase` string, required
    - `output_format` string
    - `json_schema` object, nullable
    - `outputs` AIOutputFieldDto[], required
      - `name` string, required
      - `type` string, required
    - `column_mappings` AIColumnMappingDto[]
      - `output_field` string, required
      - `column_id` string, required
      - `column_name` string, required
    - `list_id` integer, nullable
    - `is_global` boolean
    - `created_by` string, nullable
    - `created_at` string, nullable
    - `updated_at` string, nullable
    - `org_id` string, nullable
  - `run_immediately` false: Always false. Saving never runs - the app refuses immediate execution so a save can never become an unpriced spend.
  - `target_records` string[], nullable

## Response `201`

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/2e7cfa0ca921?raw)