---
date: 2025-11-05
title: "Langfuse for Agents"
badge: Launch Week 4 🚀
description: Trace agents with beautifully rendered tool calls and understand their performance through Agent Evals.
author: Nimar
ogImage: /images/changelog/2025-11-05-langfuse-for-agents/2025-11-05-agent-tools.png
---

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 Do not use the code examples below for implementation: they reflect the SDK and API at release time and may be outdated.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

Our users increasingly trace agentic applications in Langfuse, so we want to make Langfuse better for understanding agents.

## What's New

### Agent Tools

Tool calls are the heartbeat of agents. We now render all tools available to an LLM at the top of each generation, allowing you to instantly see if the LLM selected the right one.
You can click on any tool to reveal its full definition, description, and parameters. In the Chat UI, we also now display called tools alongside their arguments and call IDs. The numbering matches the available tools list, making it easy to validate performed calls against available options.

![Agent Tools](/images/changelog/2025-11-05-langfuse-for-agents/lw4-d3-tools.png)

### Trace Log View

We're rolling out a new Log View for traces—a single concatenation of all data in a trace's observations. You can now skim every agent step just by scrolling.
This view also makes it simple to CMD/Ctrl+F through an entire trace. This is a superpower when you need to find specific details inside very loopy, verbose agents.

![Trace Log View](/images/changelog/2025-11-05-langfuse-for-agents/lw4-d3-log.png)

### Observation Types

We’ve expanded the supported observation types to bring more meaning to your spans. Now, you can easily identify the type of action an observation represents, such as tool calls, embeddings or agents.

![Observation Types](/images/changelog/2025-11-05-langfuse-for-agents/lw4-d3-observation-types.png)

### Agent Graphs GA

Agent graphs are now Generally Available and works with any agent framework or custom instrumentation. We infer the graph structure from observation timings and nesting to visualize the true flow of your agent's execution, especially useful for navigating complex looping observations.

![Agent Graphs](/images/changelog/2025-11-05-langfuse-for-agents/lw4-d3-graphs.png)

## Get started

- [Observation Types Documentation](/docs/observability/features/observation-types)
- [Agent Graph Documentation](/docs/observability/features/observation-types)
- [See all Launch Week releases](/blog/2025-10-29-launch-week-4)

<!-- 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/2025-11-05-langfuse-for-agents.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>.