---
date: 2026-09-07
title: Run evaluators on historical observations
description: Backfill scores for recent observations when you attach an evaluator to a rule.
author: Tobias Wochinger
ogImage: /images/changelog/2026-09-07-evaluator-backfills.png
canonical: /docs/evaluation/core-concepts#backfill-evaluator-scores
---

> **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 Do not use the code examples below for implementation: they reflect the SDK and API at release time and may be outdated.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 canonical documentation for this feature (https://langfuse.com/docs/evaluation/core-concepts#backfill-evaluator-scores) and the API/SDK reference (https://api.reference.langfuse.com).

You can now run an evaluator on recent historical observations when you attach it to a rule. Enable **Also run on past observations** to start with scores for existing data while the rule evaluates new observations as they arrive.

Use the backfill to start an online evaluation with scores for observations that arrived before you enabled its rule. For testing an evaluator on selected historical observations or running a one-off evaluation, use [batch evaluation](/docs/evaluation/core-concepts#batch-evaluation).

- [Online evaluation](/docs/evaluation/core-concepts#backfill-evaluator-scores)
- [Batch evaluation](/docs/evaluation/core-concepts#batch-evaluation)

<!-- 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/2026-09-07-evaluator-backfills.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>.