---
date: 2026-06-19
title: Langfuse Assistant
description: The Langfuse Assistant is now in public beta for everyone on Langfuse Cloud. Ask questions about your traces, observations, and metrics in plain language.
author: Ben Bachem
ogVideo: https://static.langfuse.com/docs-videos/in-app-agent.mp4
---

> **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 Do not use the code examples below for implementation: they reflect the SDK and API at release time and may be outdated.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).

The Langfuse Assistant is now available to everyone on Langfuse Cloud. No opt-in, no Feature Preview modal. Open it and start asking questions about your data.

Ask in plain language. For example:

- "Which traces had the highest latency yesterday?"
- "Show me failed generations in the last hour."
- "What's my token spend this week, broken down by model?"

## How it works

The Assistant runs on the [Langfuse MCP server](/docs/api-and-data-platform/features/mcp-server), the same MCP server you can connect to your own tools. It uses those tools to query your traces, observations, and metrics, then answers in context.

This is the initial release. More capabilities will follow.

The Assistant is Langfuse Cloud only and still labeled Beta. It is free during the Beta, though pricing may change later.

## Feedback

We're excited to launch the Assistant, but it's still in its early stages. We would love to hear your feedback on how it's working for you, what you like, and what could be improved. We also want to know what you think the next agentic features in Langfuse should look like. Please share your thoughts in our [feedback discussion](https://github.com/orgs/langfuse/discussions/14196).

<!-- 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/2026-06-19-langfuse-assistant-public-beta.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>.