---
title: "Autogen Llm Scorer"
method: POST
path: "/public/v2/scorers/llm/autogen"
tags: ["data", "prompts", "rows"]
---

# Autogen Llm Scorer

`POST /public/v2/scorers/llm/autogen`

## Request

- Base URL: `https://api.galileo.ai`
- URL: `https://api.galileo.ai/public/v2/scorers/llm/autogen`
- Auth: one of:
  - API key in header `Splunk-AO-API-Key`
  - API key in header `Galileo-API-Key`
  - OAuth 2
    - Password
    - Token URL: `https://api.galileo.ai/login`
  - HTTP basic

Autogenerate an LLM scorer configuration.

Returns a Celery task ID that can be used to poll for the autogeneration results.

## Request body

- CreateLLMScorerAutogenRequest
  - `instructions` string, required
  - `model_name` string, required
  - `output_type` 'boolean' | 'categorical' | 'count' | 'discrete' | 'freeform' | 'percentage' | 'multilabel' | 'retrieved_chunk_list_boolean' | 'boolean_multilabel' | 'boolean_probability', required: Enumeration of output types.
  - `cot_enabled` boolean, required
  - `scoreable_node_types` string[], required

## Response `200`

Successful Response

- GenerationResponse
  - `task_result_id` string, uuid4, required

## Other responses

- `422`: Validation Error

## Changes

> 34 revisions in range; 2 not diffed.

- **2026-10-03** `fede84842199`: 1 info
  - added the new `boolean_probability` enum value to the request property `output_type`
- **2026-07-26** `05003e7835a2`: 1 info
  - the endpoint scheme security `ClassicAPIKeyHeader` was added to the API

[Operation history](https://skmtc.dev/galileo/apis/galileo-api-server/changes/public/v2/scorers/llm/autogen/post.md)

---

[API](https://skmtc.dev/galileo/apis/galileo-api-server.md) - [All operations](https://skmtc.dev/galileo/apis/galileo-api-server/llms.txt) - [OpenAPI document](https://skmtc.dev/galileo/apis/galileo-api-server/revisions/a289cea1b504?raw)