---
date: 2024-09-17
title: Link prompts to Langchain executions
description: Prompt management just got more powerful for Langchain users by linking Langfuse prompts to Langchain executions.
author: Hassieb
ogImage: /images/changelog/2024-09-17-prompt-link-langchain-trace.png
canonical: /docs/prompt-management/features/link-to-traces
---

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 Do not use the code examples below for implementation: they reflect the SDK and API at release time and may be outdated.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

We have just released one of the [most requested](https://github.com/orgs/langfuse/discussions/2237) features for Langfuse prompt management: linking Langfuse prompts to Langchain executions to benefit from detailed insight on prompt usage.

With the link established between a prompt managed in Langfuse and its corresponding Langchain executions, the performance of each given prompt can be tracked on the Langfuse platform.

In the trace view on the Langfuse platform you will notice your prompt link appearing alongside your Langchain generation. You may also filter your generations for a given prompt in the generations table and list all generations that originated from a prompt in the prompt detail view.

**Learn more**

- [Documentation](/docs/prompts/get-started#link-with-langfuse-tracing-optional)
- [Python Cookbook Prompt Management with Langchain](/docs/prompts/example-langchain)
- [JS Cookbook Prompt Management with Langchain](/docs/prompts/example-langchain-js)
- [Python SDK release](https://github.com/langfuse/langfuse-python/releases/tag/v2.49.0)
- [JS SDK release](https://github.com/langfuse/langfuse-js/releases/tag/v3.25.0)

<!-- 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/2024-09-17-prompt-linking-langchain.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>.