---
title: How to create and manage Score Configs in Langfuse?
description: Learn how to create and manage score configs in Langfuse.
tags: [evaluation]
---

# How to Create and Manage ScoreConfigs?

`ScoreConfigs` are used to ensure that your scores follow a specific schema. Using `ScoreConfigs` allows you to standardize your scoring schema across your team and ensure that scores are consistent and comparable for future analysis.

`ScoreConfigs` are **required** for using [Human Annotation](/docs/evaluation/evaluation-methods/annotation) and **optional** for [Custom Evaluation via API/SDK](/docs/evaluation/evaluation-methods/custom-scores).

`ScoreConfigs` are immutable. However, you can archive configs if you no longer want to use them in annotation. Archived configs can be restored at any time.

To understand detailed properties of the `ScoreConfig` object, see [Scores Data Model](/docs/evaluation/scores/data-model#score-config).

## Via SDK

### Create or Update a Score Config

To create or update a `scoreConfig` via the Langfuse SDK you need to use the `api` property on the Langfuse client as specified [here](/docs/api-and-data-platform/features/public-api#access-via-sdks). The specific `POST`, `PATCH` and `GET` API endpoints are documented in the [API reference](/docs/api).

### Use a Score Config

Using `ScoreConfig` via the SDK most commonly happens in the context of [Custom Evaluation via API/SDK (find instructions how to do that here)](/docs/evaluation/evaluation-methods/custom-scores#score-ingestion-referencing-configs-via-sdk).

## Via Langfuse UI

### Create a Score Config

<Steps>

#### Go to Project Settings

Navigate to `Your Project` > `Project Settings` > `Scores / Evaluation` and click `Create new score config`.

  ![Score Configs](/images/docs/scoreconfigs.png)

#### Add new score config

  ![Score Configs](/images/docs/add_new_score_config.png)

Set the values:

- **Score name**:
- **Data type**: NUMERIC, CATEGORICAL, BOOLEAN, TEXT
- **Constraints on score value range** (Min/Max for numerical, Custom categories for categorical data)

Click **"submit"** to create the score config.

</Steps>

### Use a Score Config

Using `ScoreConfig` via the UI most commonly happens in the context of [Human Annotation](/docs/evaluation/evaluation-methods/annotation).

### Update a score config

<Steps>

#### Go to Project Settings

Navigate to `Your Project` > `Project Settings` > `Scores / Evaluation` and click on the "edit" icon of the score config you want to update.

  ![Score Configs](/images/docs/modify_score_config.png)

#### Update score config

- Score configs may be updated at any time.
- All existing score data remains unaffected when you update a score config.
- When creating new scores, they must comply with the current score config schema at the time of creation.
- When updating existing scores (such as changing score values or comments), they must comply with the score config schema that is active at the time of the update.
- You can always delete scores regardless of whether their associated score config has been modified or archived.

</Steps>

### Archive a score config

<Steps>

#### Go to Project Settings

Navigate to `Your Project` > `Project Settings` > `Scores / Evaluation` and click on the "archive" icon of the score config you want to archive.

  ![Score Configs](/images/docs/modify_score_config.png)

#### Archive score config

- Archiving a score config will ensure that the score config is no longer selectable for [Human Annotation](/docs/evaluation/evaluation-methods/annotation).
- You will be able to restore a config by clicking the "archive" icon of an archived config.
- Scores associated with an archived config will still be shown in your project but can be deleted.

</Steps>

<!-- agent-instructions -->

---

## Agent Instructions

This page is part of the [Langfuse](https://langfuse.com) documentation, published as plain Markdown for AI agents. Every page is available as Markdown by appending `.md` to its URL, or by sending an `Accept: text/markdown` header. This page: `https://langfuse.com/faq/all/manage-score-configs.md`.

### Querying these docs

If the answer is not on this page, query the documentation instead of guessing:

- **Semantic search** across all Langfuse docs, returning an answer with the relevant pages and excerpts. Ask a specific, self-contained question:

  ```bash
  curl -sG "https://langfuse.com/api/search-docs" --data-urlencode "query=How do I trace a LangGraph agent?"
  ```

- **Index of every page**: <https://langfuse.com/llms.txt>, with per-section indexes [llms-docs.txt](https://langfuse.com/llms-docs.txt), [llms-integrations.txt](https://langfuse.com/llms-integrations.txt), and [llms-self-hosting.txt](https://langfuse.com/llms-self-hosting.txt).

### Before writing Langfuse code

- **Install the [Langfuse Agent Skill](https://langfuse.com/docs/api-and-data-platform/features/agent-skill).** It encodes Langfuse's own best practices for instrumentation, prompt management, and evaluation, and materially improves results.
- **Read [What does a good trace look like?](https://langfuse.com/docs/observability/best-practices.md)** before instrumenting an application.
- **Verify endpoints, parameters, and response fields** against the [API reference](https://api.reference.langfuse.com) instead of inferring them from code examples.
- **Use the [Langfuse CLI](https://langfuse.com/docs/api-and-data-platform/features/cli)** (`npx langfuse-cli api <resource> <action>`) to read or write traces, prompts, datasets, and scores from the terminal.

Found an error in these docs? Please open an issue at <https://github.com/langfuse/langfuse-docs/issues>.