Customer stories

“We wanted something built for agents as users first. And that means API first. An agent should never get stuck waiting for a human because of a deficiency in the API. This is what Langfuse is.”

Video story

David TrainaData Platform

90B+

Observations / month

Of the Fortune 50

37.3k

GitHub stars

100+

Integrations

Learn from teams building AI on Langfuse

Real deployments across support agents, tutoring, design tools, and enterprise AI platforms. How teams trace, monitor and improve with Langfuse.

How Ramp Uses Langfuse to Build AI Agents That Improve Themselves

“We wanted something built for agents as users first. And that means API first. An agent should never get stuck waiting for a human because of a deficiency in the API. This is what Langfuse is.”

Watch the video

How Canva built an Agentic Support Experience using Langfuse

“Langfuse hits the sweet spot between engineering requirements and empowerment of non-technical users to contribute their domain expertise.”

Read the story

Khan Academy uses Langfuse's AI Engineering platform to build Khanmigo AI

“Langfuse has enabled our developers to get extremely fast feedback. It's fundamental to how our developers understand their AI implementations.”

Read the story

How DKB uses Langfuse to keep its AI banking assistant accurate, compliant, and trustworthy at scale

“The whole pipeline to improve our chat agent happens entirely in Langfuse. Engineers and domain experts work hand-in-hand.”

Read the story

How Merck is serving 80+ AI project teams globally on Langfuse

“Langfuse enables us to track every prompt, response, cost, and latency in real time, turning black-box models into auditable, optimizable assets.”

Read the story

AI-Powered first level support for 4 million merchants

“Building on Langfuse we saved 30% of external BPO cost by deflecting 50% of support conversations to AI.”

Read the story

How Trade Republic migrates live LLM workflows to agentic harnesses with Langfuse

“You can connect Claude Code to your Langfuse MCP - or the CLI directly - and it starts fixing and trying until it is fixed.”

Watch the video

How Hugging Face Scales Open-Source Model Discovery with Agents and Langfuse

“In just a few minutes you're up and running, and you're already able to see what's going on.”

Read the story

How Cresta traces multi-service AI agent pipelines with Langfuse

“Langfuse has made it a lot easier for us at Cresta to iterate on LLM behavior. It has sped up how quickly we can test, learn, improve the model, and build great AI agents.”

Read the story