---
title: "Why does Langfuse exist?"
description: "Why Langfuse exists: to accelerate the deployment of reliable, safe, explainable, and cost-effective AI applications and agents."
---

# Why does Langfuse exist?

Langfuse exists to accelerate the deployment of reliable, safe, explainable and cost-effective AI applications and agents.

AI will create meaningful value for society and drive economic growth and we are still in the early days of seeing this impact. Over time, every successful company will be an AI company, with AI at the core of its strategy, value creation, and business processes. Most value creation will happen at the application-layer, split between incumbents and AI-native startups.

We’re building an [integrated](/integrations) and [open](/handbook/chapters/open-source) tooling layer to help teams with:

- **Visibility & explainability** → _Langfuse Observability_ (production tracing, metrics, and analytics)
- **Collaboration across disciplines** → _Prompt management, shareable views & dashboards_
- **Evaluation & data operations** → _Langfuse Evaluations (evals, datasets, labeling)_

We are independent, vendor-neutral, and available as cloud or self-hosted at production scale.

## Where are we going?

The ecosystem evolves quickly.

Model capabilities improve, inference gets cheaper, and agents can work longer on harder problems. As this happens, the focus shifts from **“How do we make it work?”** to **“How does it work? How do we improve it? And who is accountable?”**

Our bet:

- **Production tracing is the source of truth** for AI applications and agents.
- **Evals are a means to an end**, closing the loop from experiment to production and back.
- Teams need a **neutral observability and data layer** to understand, govern, and continuously improve AI systems at scale, while the underlying models, frameworks and technologies evolve.

<!-- 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/handbook/chapters/mission.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>.