langfuse.com

Open source LLM engineering platform. Now part of @clickhousedb. We're hiring:

[langfuse.com @langfuse]

Building high-quality AI systems is hard.

At Langfuse we see the best AI teams converging on a process to get complex AI systems to production.

We call it the AI Engineering Loop.

Check out the first piece of our series and find out more in our academy

[Annabell @annabellschfr]

https://t.co/jT1XJ8Ru6o

[Marc Klingen @marcklingen]

had a lot of fun at the AI Engineer conference to go deep on:
(1) how we think about the role of skills
(2) how to develop/eval/improve them
(3) lessons from building our own set of skills

[langfuse.com @langfuse]

quarterly Langfuse Town Hall on June 11th

catch up on everything we've shipped: v4, the latest releases, and what's coming next on the roadmap. Q&A with the team at the end.

open to the whole community. register: https://t.co/2hMFvMY62j

[langfuse.com @langfuse]

The Vercel AI x Langfuse integration finally has a proper walkthrough video. No excuses not to set it up now.

[Clemens Rawert @rawert]

team langfuse will be hanging out at the grove on wednesday this week. Meet us for coffee and drinks in the pm --> https://t.co/WBeckwM8Iy

[langfuse.com @langfuse]

Coming to SF for Snowflake Summit? Meet our team next to Moscone for coffee, drinks & database + agent observability talk

https://t.co/LRcQpghyQS

cc @ClickHouseDB

[langfuse.com @langfuse]

day 5 of launch week: langfuse MCP.

supports: observations, metrics, scores, datasets, comments, annotation queues, models, media, and more.

claude or linear agents can pull a trace, drop a comment, or create dataset items without leaving the chat.

https://t.co/jBHM8WeA5e

[langfuse.com @langfuse]

day 4 of langfuse launch week: code evaluators.

write a python or typescript `evaluate` function in the langfuse UI. attach it to live observations or an experiment. scores land natively next to your existing ones.

@wochinge demos below; https://t.co/jBHM8WeA5e

[langfuse.com @langfuse]

day 3 of langfuse launch week: full-text search.

multi-GB scans drop from many seconds to sub-second on @ClickHouseDB's new text indexes. great work from @sum3rman.

available via UI and API.

more: https://t.co/jBHM8WeA5e

[langfuse.com @langfuse]

day 2 of langfuse launch week 5: langfuse agent skill.

bringing an agent to production is hard.

using the skill you can ask your coding agent to instrument your app, calibrate a judge, or set up evaluators.

@marliessophie demos below; https://t.co/jBHM8WeA5e

[langfuse.com @langfuse]

day 1 of langfuse launch week 5: a github action that runs your langfuse experiments on every PR.

fails the workflow when scores drop below your threshold. posts pass/fail to the PR. every run is tracked in langfuse.

https://t.co/jBHM8WeA5e

[langfuse.com @langfuse]

day 1 of langfuse launch week 5: a github action that runs your langfuse experiments on every PR.

fails the workflow when scores drop below your threshold. posts pass/fail to the PR. every run is tracked in langfuse.

https://t.co/jBHM8WeA5e

[langfuse.com @langfuse]

@langfuse launch week 5 starts monday.

one release per day, mon to fri. agents, evals, and some long-requested features.

we'll be demoing all new features at @ClickHouseDB Open House in San Francisco same week. come say hi.

https://t.co/isf5XmqcVr

[langfuse.com @langfuse]

@langfuse launch week 5 starts monday.

one release per day, mon to fri. agents, evals, and some long-requested features.

we'll be demoing all new features at @ClickHouseDB Open House in San Francisco same week. come say hi.

https://t.co/isf5XmqcVr

[langfuse.com @langfuse]

Want to see what Claude Code is actually doing? We made a video showing exactly how to observe it in real-time with Langfuse.

Claude Code in Action: Trace Tool Calls & Decisions with Langfuse https://t.co/p58PHR8Ssj

[langfuse.com @langfuse]

closing out the academy with evaluation

manual review, code-based checks, and llm-as-a-judge, and how to combine them

[Lotte @lotte_verheyden]

https://t.co/Ek978h3JOB

[langfuse.com @langfuse]

good experiments require strategy and taste

understand the fundamentals before trying to automate them

[Annabell @annabellschfr]

https://t.co/mY1djavsrJ

[Clemens Rawert @rawert]

This is a great article by @annabellschfr - a lot of teams still get stucks on vibes and don't make it to actually systematically experiment with models, prompts, . context, architectures. dig in!

[langfuse.com @langfuse]

don't ship blind, build your datasets

[Lotte @lotte_verheyden]

https://t.co/wGEdZy4IG6

[langfuse.com @langfuse]

good read on monitoring for llm apps 👀

[Annabell @annabellschfr]

https://t.co/ATLt91eLEe