---
title: "How Trade Republic migrates live LLM workflows to agentic harnesses with Langfuse"
seoTitle: "How Trade Republic migrates live LLM workflows to agentic harnesses with Langfuse"
date: September 18, 2026
description: "Trade Republic's Ops Tools team on self-hosted Langfuse, and how homework and exam datasets make migrating production LLM processes to ReAct agents safer."
ogImage:
tag: customer-story
customerLogo: "/images/customers/trade-republic/trade-republic-light.png"
customerLogoDark: "/images/customers/trade-republic/trade-republic-dark.png"
customerQuote: "We're using the open-source self-hosted version of Langfuse and we don't see any limitations there. We're super happy with it."
customerQuoteHighlight: "don't see any limitations"
customerQuoteTag: "Video story"
quoteAuthor: "Paolo Tamagnini"
quoteRole: "Senior Data Scientist"
quoteCompany: "Trade Republic"
ctaLabel: "Watch"
showInCustomerIndex: true
---

[Customer stories](/users) › Trade Republic

<iframe
  width="100%"
  src="https://www.youtube-nocookie.com/embed/spDdtN__nQQ?rel=0"
  title="How Trade Republic migrates live LLM workflows to agentic harnesses with Langfuse"
  frameBorder="0"
  allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share"
  referrerPolicy="strict-origin-when-cross-origin"
  className="aspect-video w-full rounded border mt-2"
  allowFullScreen
></iframe>

<p className="text-sm text-primary/60 mt-2 mb-8">
  <a href="https://www.youtube.com/watch?v=spDdtN__nQQ">Watch on YouTube</a>
</p>

## Highlights from the talk [#highlights-from-the-talk]

[Trade Republic](https://traderepublic.com/) is one of Europe's largest fintechs and a fully licensed bank, with over 10 million customers and €150 billion in assets under management. In this talk, Paolo Tamagnini (Senior Data Scientist, Ops Tools) explains how the team uses [self-hosted](/self-hosting) Langfuse to migrate production LLM processes - sequenced prompts with predetermined flows - into more modern ReAct agent architectures with tools.

They started with Langfuse about two years ago on Postgres, then upgraded to ClickHouse when they moved to a newer version, and rolled it out from a single team to more teams while clearing bank compliance requirements.

> “We're using the open-source self-hosted version of Langfuse and we don't see any limitations there. We're super happy with it.”
>
> — Paolo Tamagnini, Senior Data Scientist, Trade Republic

Many of their early "LLM processes" were easy for product teams to sketch in Figma and inspect in Langfuse: summarize an incident, classify it, score severity, trigger an action. That pattern worked well with earlier models. As reasoning models improved, they wanted agentic setups where a single prompt calls tools instead of a fixed chain of isolated prompts - but the workflows were already in production, so a naive rewrite was too risky.

Their answer is Langfuse plus the evaluation flywheel: [trace](/docs/observability/overview) every run, [score](/docs/evaluation/scores/overview) good and bad examples (human annotation, deterministic checks, or [LLM-as-a-Judge](/docs/evaluation/evaluation-methods/llm-as-a-judge)), fix failures (including via coding agents connected through the Langfuse MCP or CLI), and store cases in [datasets](/docs/evaluation/experiments/datasets). For architecture migrations they split data into a homework set (for iterating prompts and tools) and an exam set (held-out topics so coding agents cannot few-shot memorize the fix). An LLM judge compares the deployed workflow against the ReAct agent; only when both sets pass do they ship.

> “You start with the homework set… you have your already deployed workflow and your ReAct agent, you make them compete, and a custom LLM judge scores the trace. Then you need the exam dataset to see if the issue was actually fixed - because coding agents are smart and can simply few-shot the homework.”
>
> — Paolo Tamagnini, Senior Data Scientist, Trade Republic

## Ready to get started with Langfuse?

Join thousands of teams building better LLM applications with Langfuse's open-source observability platform.

- [Start free](/cloud)
- [Documentation](/docs)
- [Talk to an expert](/talk-to-us)

<!-- 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/users/trade-republic.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>.