---
date: 2026-01-14
title: Corrected Outputs for Traces and Observations
description: Capture improved versions of LLM outputs directly in trace views. Build fine-tuning datasets and drive continuous improvement with domain expert feedback.
author: Marlies
ogImage: /images/changelog/2026-01-15-corrected-output.jpg
canonical: /docs/observability/features/corrections
---

> **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 Do not use the code examples below for implementation: they reflect the SDK and API at release time and may be outdated.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/observability/features/corrections) and the API/SDK reference (https://api.reference.langfuse.com).

You can now add corrected outputs to traces and observations, making it easy for domain experts to capture what the model should have generated. View diffs between original and corrected outputs, and export corrections to build better datasets.

## Why corrections matter

**Human-in-the-loop improvement**: Domain experts review production outputs and provide corrections based on their expertise. Capture institutional knowledge directly in your traces.

**Fine-tuning data at scale**: Export corrected outputs alongside original inputs to create high-quality training datasets from real production data.

**Quality benchmarking**: Compare actual vs expected outputs across your production traces. Identify systematic issues and track improvement over time.

## How it works

Navigate to any trace or observation and add a corrected output in the dedicated field. Langfuse shows a diff view comparing the original and corrected outputs. Toggle between JSON validation mode and plain text to match your data format.

Corrections are accessible via the API as scores with `dataType: "CORRECTION"`, making it easy to export and analyze them programmatically.

## Use cases

- **Customer support**: Capture expert agent responses for training
- **Content generation**: Document preferred outputs for style and tone
- **Code generation**: Record working code when the model output needed fixes
- **Structured extraction**: Provide correctly formatted outputs as examples

## Learn more

- [Corrections Documentation](/docs/observability/features/corrections)
- [Share Feedback on GitHub](https://github.com/orgs/langfuse/discussions)

<!-- 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/2026-01-14-corrected-outputs.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>.