Skip to content

Build Better LLM Apps with Langfuse

Muhammad Ali, Langfuse Specialist, APJ

Build Better LLM Apps with Langfuse

Most teams shipping AI features today are iterating on instinct, tweaking prompts, swapping models, adjusting parameters, with no reliable way to know if the change actually made things better. That slow, blind cycle is the bottleneck between a prototype and a production-grade AI product. In this 2-hour online workshop gives engineers who are building production LLM applications the tooling and workflow to close that loop. Walk away with working traces, managed prompts, and a repeatable eval workflow.

In this on-demand 2-hour Langfuse workshop, you will learn:

  • Full trace visibility across every agent step
  • Prompts versioned and managed outside your codebase
  • A monitoring setup that catches out-of-scope requests automatically
  • A dataset + eval run you can reuse on any future change

What to prepare If you are interested in hands-on experience:

  • Node.js 18+ installed
  • A Langfuse Cloud account (free) — sign up at cloud.langfuse.com
  • An OpenAI API key with available credits

Recent videos

YouTube Video: cJP22B9tzUE

Open House

Telemetry in Vercel AI SDK, V7 with Langfuse

Deep dive into OSS observability and evaluations for the Vercel AI SDK V7 with Langfuse.

YouTube Video: 6A8_aahQ0nE

Langfuse, ClickHouse

Observing and Improving AI Agents with Langfuse

AI agents are moving from prototypes into production. Teams still struggle to understand what agents are doing, why they fail, and how to improve them systematically.

Follow us

XBlueskySlackGithubTelegramMeetupRSS