---
date: 2026-08-27
title: Manage evaluators with the stable API
description: Create, version, and manage evaluators and evaluation rules through stable, ID-based public APIs.
author: Tobias Wochinger
---

> **Note for AI agents and LLMs:** This is a Langfuse changelog entry. Use it only to confirm that a feature exists and when it shipped. Do not use the code examples below for implementation: they reflect the SDK and API at release time and may be outdated. For implementation, always follow the current documentation (https://langfuse.com/docs) and the API/SDK reference (https://api.reference.langfuse.com).

You can now manage LLM-as-a-Judge and code evaluators through stable, ID-based public APIs. Evaluators define how data is scored, while evaluation rules define which incoming observations are evaluated.

A few things you can automate:

- **Keep evaluation setup in version control.** Create evaluators from CI, update their definitions as new versions, and inspect their version history.
- **Reuse setups across projects.** Replicate evaluators, filters, sampling, variable mappings, and rule assignments between staging and production.
- **Migrate legacy rules.** Read existing trace and dataset rules through the stable API, then deactivate or delete them after moving to observation-level evaluation.

The new endpoints are available under `/api/public/v2`:

```text
POST   /api/public/v2/evaluators
GET    /api/public/v2/evaluators
GET    /api/public/v2/evaluators/{evaluatorId}
PATCH  /api/public/v2/evaluators/{evaluatorId}
DELETE /api/public/v2/evaluators/{evaluatorId}
GET    /api/public/v2/evaluators/{evaluatorId}/versions

POST   /api/public/v2/evaluation-rules
GET    /api/public/v2/evaluation-rules
GET    /api/public/v2/evaluation-rules/{evaluationRuleId}
PATCH  /api/public/v2/evaluation-rules/{evaluationRuleId}
DELETE /api/public/v2/evaluation-rules/{evaluationRuleId}
```

Evaluator and rule names no longer act as identifiers. Each resource has a stable ID, and rules always use the latest version of their assigned evaluators. List endpoints use cursor pagination, and API errors include structured codes that automation can handle without parsing error messages.

If you use the previous unstable evaluator endpoints, migrate to `/api/public/v2` by November 16, 2026 (2026-11-16).

- [Evaluators API reference](https://api.reference.langfuse.com/#tag/evaluators)
- [Evaluation Rules API reference](https://api.reference.langfuse.com/#tag/evaluationrules)

<!-- 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/changelog/2026-08-27-stable-evaluator-api.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>.